KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#developer-tools #typescript #dsh #dsh-plugin #ai-agent #codex #ai-agents #deepseek-harness #claude-code #cli #react #mcp

Unsupervised-Visual-Representation-Learning

★ 38 Open GitHub ↗

Overview of unsupervised visual representation learning (or self-supervised learning, unsupervised pre-training) methods.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Unsupervised/Self-Supervised-Visual-Representation-Learning 
## 无监督/自监督视觉表示学习

**[ Updating ...... ]**

Unsupervised visual representation learning (UVRL) aims at learning generic representations for the initialization of downstream tasks. 
As stated in MoCo, self-supervised learning is a form of unsupervised learning and their distinction is informal in the existing literature. Therefore, it is more inclined to be called UVRL here. So, which one do you prefer?

We list related papers from conferences and journals such as **[CVPR](https://openaccess.thecvf.com/menu)**, **[ICCV](https://openaccess.thecvf.com/menu)**, **[ECCV](https://www.ecva.net/)**, **[ICLR](https://openreview.net/group?id=ICLR.cc&referrer=%5BHomepage%5D(%2F))**, **[ICML](https://proceedings.mlr.press/)**, **[NeurIPS](https://nips.cc/)**, **[AAAI](https://aaai.org/Library/conferences-library.php)**, **[IJCAI](https://www.ijcai.org/)**, **[TPAMI](https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34)**, **TIP**, **TNNLS**, **TCSVT**, **TMM** etc.

Note that only image-level representation learning methods are listed in this repository. [Video-level self-supervision](https://github.com/zhangyifei01/Self-supervised-Video-Representation-Learning) and multi-modal self-supervision are to be sorted out.

**Key words:** Unsupervised learning, self-supervised learning, representation learning, pre-training, transfer learning, contrastive learning, pretext task

**关键词：** 无监督学习，自监督学习，表示学习，预训练，迁移学习，对比学习，借口（代理）任务

## 2023

***
- Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations (**** - **ICLR**23 ) [[paper]](https://openreview.net/forum?id=jwdqNwyREyh) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Ziyu Jiang, Yinpeng Chen, Mengchen Liu, Dongdong Chen, Xiyang Dai, Lu Yuan, Zicheng Liu, Zhangyang Wang 
 · · Organization(s): Texas A&M University; Microsoft; University of Texas at Austin 
 · · Description: 
 · · Tags: CL, MIM
 </details>
***
- Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning (**ADCLR** - **ICLR**23 ) [[paper]](https://openreview.net/forum?id=10R_bcjFwJ) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan 
 · · Organization(s): Shanghai Jiao Tong University; SenseTime Group Limited 
 · · Description: 
 · · Tags: Dense
 </details>
***
- Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning (**SNCLR** - **ICLR**23 ) [[paper]](https://openreview.net/forum?id=l9vM_PaUKz) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Chongjian GE, Jiangliu Wang, Zhan Tong, Shoufa Chen, Yibing Song, Ping Luo 
 · · Organization(s): HongKong University and so on 
 · · Description: 
 · · Tags: Soft neighbor
 </details>

***
- Energy-Inspired Self-Supervised Pretraining for Vision Models (**** - **ICLR**23 Spotlight ) [[paper]](https://openreview.net/forum?id=ZMz-sW6gCLF) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Ze Wang, Jiang Wang, Zicheng Liu, Qiang Qiu 
 · · Organization(s): Purdue University; Microsoft Corporation 
 · · Description: 
 · · Tags: Energy
 </details>

***
- EquiMod: An Equivariance Module to Improve Self-Supervised Learning (**EquiMod** - **ICLR**23 ) [[paper]](https://openreview.net/forum?id=eDLwjKmtYFt) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Alexandre DEVILLERS, Mathieu Lefort 
 · · Organization(s): Université Claude Bernard 
 · · Description: 
 · · Tags: Equivariance
 </details>

***
- Mosaic Representation Learning for Self-supervised Visual Pre-training (**MosRep** - **ICLR**23 Spotlight ) [[paper]](https://openreview.net/forum?id=JAezPMehaUu) [[code]](https://github.com/DerrickWang005/MosRep)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhaoqing Wang, Ziyu Chen, Yaqian Li, Yandong Guo, Jun Yu, Mingming Gong, Tongliang Liu 
 · · Organization(s): The University of Sydney 
 · · Description: 
 · · Tags: 
 </details>

***
- Temperature Schedules for self-supervised contrastive methods on long-tail data (**** - **ICLR**23 ) [[paper]](https://openreview.net/forum?id=ejHUr4nfHhD) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Anna Kukleva, Moritz Böhle, Bernt Schiele, Hilde Kuehne, Christian Rupprecht 
 · · Organization(s): Saarland Informatics Campus, Max-Planck Institute 
 · · Description: 
 · · Tags: Long-tail
 </details>

## 2022

***
- LPCL: Localized prominence contrastive learning for self-supervised dense visual pre-training (**LPCL** - **PR**22) [[paper]](https://www.sciencedirect.com/science/article/pii/S0031320322006641) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Zihan Chen, Hongyuan Zhu, Hao Cheng, Siya Mi, Yu Zhang, Xin Geng 
 · · Organization(s): Southeast University; A*STAR; Purple Mountain Laboratories 
 · · Description: 
 · · Tags: Dense
 </details>
***
- Self-supervised Learning is More Robust to Dataset Imbalance (**** - **ICLR**22 Spotlight) [[paper]](https://openreview.net/forum?id=4AZz9osqrar) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma 
 · · Organization(s): Stanford University; Toyota Research Institute 
 · · Description: 
 · · Tags: Analysis, Imbalance data
 </details>
***
- Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap (**** - **ICLR**22) [[paper]](https://openreview.net/forum?id=ECvgmYVyeUz) [[code]](https://github.com/zhangq327/ARC)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yifei Wang, Qi Zhang, Yisen Wang, Jiansheng Yang, Zhouchen Lin 
 · · Organization(s): Peking University; Sun Yat-sen University; Peng Cheng Laboratory 
 · · Description: 
 · · Tags: Analysis 
 </details>
***
- How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning (**** - **ICLR**22) [[paper]](https://openreview.net/forum?id=bwq6O4Cwdl) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Trung X. Pham, Chang D. Yoo, In So Kweon 
 · · Organization(s): KAIST 
 · · Description: 
 · · Tags: Analysis 
 </details>
***
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution (**LP-FT** - **ICLR**22 Oral) [[paper]](https://openreview.net/forum?id=UYneFzXSJWh) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, Percy Liang 
 · · Organization(s): Stanford University 
 · · Description: 
 · · Tags: Analysis 
 </details>
***
- Scarf: Self-Supervised Contrastive Learning using Random Feature Corruption (**Scarf** - **ICLR**22 Spotlight) [[paper]](https://openreview.net/forum?id=CuV_qYkmKb3) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Dara Bahri, Heinrich Jiang, Yi Tay, Donald Metzler 
 · · Organization(s): Google Research 
 · · Description: 
 · · Tags: Tabular domain 
 </details>
***
- Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing (**QRP** - **ICLR**22) [[paper]](https://openreview.net/forum?id=HFPTzdwN39) [[code]](https://github.com/iro-cp/ssl-qrp)
 <details>
 <summary>More Info</summary>
 · · Author(s): Iro Laina, Yuki M Asano, Andrea Vedaldi 
 · · Organization(s): University of Oxford; University of Amsterdam 
 · · Description: 
 · · Tags: Interpretability 
 </details>
***
- Equivariant Contrastive Learning (Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations) (**E-SSL** - **ICLR**22) [[paper]](https://openreview.net/forum?id=gKLAAfiytI) [[code]](https://github.com/rdangovs/essl)
 <details>
 <summary>More Info</summary>
 · · Author(s): Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljacic 
 · · Organization(s): MIT; FAIR 
 · · Description: 
 · · Tags: Equivariant 
 </details>
***
- Divergence-aware Federated Self-Supervised Learning (**FedSSL** - **ICLR**22) [[paper]](https://openreview.net/forum?id=oVE1z8NlNe) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Weiming Zhuang, Yonggang Wen, Shuai Zhang 
 · · Organization(s): NTU; SenseTime Research 
 · · Description: 
 · · Tags: Federal 
 </details>
***
- Bag of Instances Aggregation Boosts Self-supervised Distillation (**BINGO** - **ICLR**22) [[paper]](https://openreview.net/forum?id=N0uJGWDw21d) [[code]](https://github.com/haohang96/bingo)
 <details>
 <summary>More Info</summary>
 · · Author(s): Haohang Xu, Jiemin Fang, XIAOPENG ZHANG, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, Qi Tian 
 · · Organization(s): Shanghai Jiao Tong University; Huawei Inc.; Huazhong University of Science & Technology 
 · · Description: 
 · · Tags: Self-supervised distillation
 </details>
***
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning (**VICReg** - **ICLR**22) [[paper]](https://openreview.net/forum?id=xm6YD62D1Ub) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Adrien Bardes, Jean Ponce, Yann LeCun 
 · · Organization(s): Facebook AI Research; Inria; New York University 
 · · Description: 
 · · Tags: 
 </details>
***
- Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning (**Zero-CL** - **ICLR**22) [[paper]](https://openreview.net/forum?id=RAW9tCdVxLj) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang 
 · · Organization(s): Shanghai Jiao Tong University; SenseTime Research 
 · · Description: 
 · · Tags: 
 </details>
***
- BEiT: BERT Pre-Training of Image Transformers (**BEiT** - **ICLR**22 Oral) [[paper]](https://openreview.net/pdf?id=p-BhZSz59o4) [[code]](https://github.com/microsoft/unilm)
 <details> 
 <summary>More Info</summary>
 · · Author(s): Hangbo Bao, Li Dong, Songhao Piao, Furu Wei 
 · · Organization(s): Harbin Institute of Technology; Microsoft Research 
 · · Description: 
 · · Tags: Transformer
 </details>

***
- Efficient Self-supervised Vision Transformers for Representation Learning (**EsViT** - **ICLR**22) [[paper]](https://openreview.net/pdf?id=fVu3o-YUGQK) [[code]](https://github.com/microsoft/esvit)
 <details> 
 <summary>More Info</summary>
 · · Author(s): Hangbo Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Mei Gao, Bin Xiao, Xiyang Dai, Lu Yuan, Jianfeng Gao 
 · · Organization(s): Microsoft Research at Redmond; Microsoft Cloud + AI 
 · · Description: 
 · · Tags: Transformer
 </details>

***
- iBOT：Image BERT Pre-Training with Online Tokenizer (**iBOT** - **ICLR**22) [[paper]](https://openreview.net/forum?id=ydopy-e6Dg) [[code]](https://github.com/bytedance/ibot)
 <details> 
 <summary>More Info</summary>
 · · Author(s): Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, Tao Kong 
 · · Organization(s): ByteDance; Johns Hopkins University; Shanghai Jiao Tong University; UC Santa Cruz 
 · · Description: 
 · · Tags: Transformer
 </details>

***
- Understanding Dimensional Collapse in Contrastive Self-supervised Learning (**** - **ICLR**22) [[paper]](https://openreview.net/forum?id=YevsQ05DEN7) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian 
 · · Organization(s): Facebook AI Research 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Incremental False Negative Detection for Contrastive Learning (**IFND** - **ICLR**22) [[paper]](https://openreview.net/forum?id=dDjSKKA5TP1) [[code]](https://github.com/tsaishien-chen/IFND)
 <details>
 <summary>More Info</summary>
 · · Author(s): Tsai-Shien Chen, Wei-Chih Hung, Hung-Yu Tseng, Shao-Yi Chien, Ming-Hsuan Yang 
 · · Organization(s): National Taiwan University; Waymo LLC; University of California, Merced; Yonsei University; Google Research 
 · · Description: 
 · · Tags: False negative
 </details>
***
- Self-Supervised Learning via Maximum Entropy Coding (**MEC** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2210.11464) [[code]](https://github.com/xinliu20/MEC)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xin Liu, Zhongdao Wang, Yali Li, Shengjin Wang 
 · · Organization(s): Tsinghua University 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Learning Through Efference Copies (**S-TEC** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2210.09224) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Franz Scherr, Qinghai Guo, Timoleon Moraitis 
 · · Organization(s): Huawei Technologies 
 · · Description: 
 · · Tags: 
 </details>
***
- VICRegL: Self-Supervised Learning of Local Visual Features (**VICRegL** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2210.01571) [[code]](https://github.com/facebookresearch/VICRegL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Adrien Bardes, Jean Ponce, Yann LeCun 
 · · Organization(s): Meta, FAIR; Inria, École normale supérieure, CNRS, PSL Research University; New York University 
 · · Description: 
 · · Tags: local feature
 </details>
***
- An Empirical Study on Disentanglement of Negative-free Contrastive Learning (**** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2206.04756) [[code]](https://github.com/noahcao/disentanglement_lib_med)
 <details>
 <summary>More Info</summary>
 · · Author(s): Jinkun Cao, Ruiqian Nai, Qing Yang, Jialei Huang, Yang Gao 
 · · Organization(s): Carnegie Mellon University; Tsinghua University; Shanghai Jiao Tong University; Shanghai Qi-Zhi Institute 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods (**** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2205.11508) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Randall Balestriero, Yann LeCun 
 · · Organization(s): Meta AI Research; NYU 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning (**** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2205.06226) 
 <details>
 <summary>More Info</summary>
 · · Author(s): RZixin Wen, Yuanzhi Li 
 · · Organization(s): Carnegie Mellon University 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Improving Self-Supervised Learning by Characterizing Idealized Representations (**** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2209.06235) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Yann Dubois, Tatsunori Hashimoto, Stefano Ermon, Percy Liang 
 · · Organization(s): Stanford University 
 · · Description: 
 · · Tags: 
 </details>
***
- MSR: Making Self-supervised learning Robust to Aggressive Augmentations (**MSR** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2206.01999) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Yingbin Bai, Erkun Yang, Zhaoqing Wang, Yuxuan Du, Bo Han, Cheng Deng, Dadong Wang, Tongliang Liu 
 · · Organization(s): TML Lab, The University of Sydney; Xidian University; JD Explore Academy; Hong Kong Baptist University; CSIRO 
 · · Description: 
 · · Tags: 
 </details>
***
- RényiCL: Contrastive Representation Learning with Skew Rényi Divergence (**RényiCL** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2208.06270) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Kyungmin Lee, Jinwoo Shin 
 · · Organization(s): Korea Advanced Institute of Science and Technology (KAIST) 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Learning of Group Invariant and Equivariant Representations (**** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2202.07559) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Robin Winter, Marco Bertolini, Tuan Le, Frank Noé, Djork-Arné Clevert 
 · · Organization(s): Bayer AG; Freie Universität Berlin; Microsoft Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Energy-Based Contrastive Learning of Visual Representations (**** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2202.04933) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Beomsu Kim, Jong Chul Ye 
 · · Organization(s): KAIST 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Visual Representation Learning with Semantic Grouping (**SlotCon** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2205.15288) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Xin Wen, Bingchen Zhao, Anlin Zheng, Xiangyu Zhang, Xiaojuan Qi 
 · · Organization(s): The University of Hong Kong; Tongji University; LunarAI; MEGVII Technology 
 · · Description: 
 · · Tags: Dense
 </details>
***
- ConvMAE: Masked Convolution Meets Masked Autoencoders (**ConvMAE** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2205.03892) [[code]](https://github.com/Alpha-VL/ConvMAE)
 <details>
 <summary>More Info</summary>
 · · Author(s): Peng Gao, Teli Ma, Hongsheng Li, Ziyi Lin, Jifeng Dai, Yu Qiao 
 · · Organization(s): Shanghai AI Laboratory; MMLab, CUHK; SenseTime Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Green Hierarchical Vision Transformer for Masked Image Modeling (**GreenMIM** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2205.13515) [[code]](https://github.com/LayneH/GreenMIM)
 <details>
 <summary>More Info</summary>
 · · Author(s): Lang Huang, Shan You, Mingkai Zheng, Fei Wang, Chen Qian, Toshihiko Yamasaki 
 · · Organization(s): The University of Tokyo; SenseTime Research; The University of Sydney 
 · · Description: 
 · · Tags: Transformer
 </details>
***
- SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders (**SemMAE** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2206.10207) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Gang Li, Heliang Zheng, Daqing Liu, Chaoyue Wang, Bing Su, Changwen Zheng 
 · · Organization(s): Institute of Software, Chinese Academy of Sciences; University of Chinese Academy of Sciences; JD Explore Academy; Renmin University of China 
 · · Description: 
 · · Tags: Transformer
 </details>
***
- Test-Time Training with Masked Autoencoders (**TTT-MAE** - **NeurIPS**22) [[paper]](https://arxiv.org/abs/2209.07522) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros 
 · · Organization(s): UC Berkeley; Meta AI 
 · · Description: 
 · · Tags: Transformer
 </details>

***
- Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning (**CMSF** - **ECCV**22) [[paper]](https://www.ecva.net/papers/eccv_2022/papers_ECCV/html/4300_ECCV_2022_paper.php) [[code]](https://github.com/UCDvision/CMSF)
 <details>
 <summary>More Info</summary>
 · · Author(s): K L Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Kossar Pourahmadi, Akshayvarun Subramanya, Hamed Pirsiavash 
 · · Organization(s): University of California, Davis; University of Maryland 
 · · Description: 
 · · Tags: NN
 </details>
***
- Relative Contrastive Loss for Unsupervised Representation Learning (**RCL** - **ECCV**22) [[paper]](https://www.ecva.net/papers/eccv_2022/papers_ECCV/html/6602_ECCV_2022_paper.php)
 <details>
 <summary>More Info</summary>
 · · Author(s): Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, and Wanli Ouyang 
 · · Organization(s): University of Sydney et.al. 
 · · Description: 
 · · Tags: soft, clustering
 </details>
***
- Improving Self-Supervised Lightweight Model Learning via Hard-Aware Metric Distillation (**SMD** - **ECCV**22 Oral) [[paper]](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910286.pdf) [[code]](https://github.com/liuhao-lh/SMD)
 <details>
 <summary>More Info</summary>
 · · Author(s): Hao Liu, Mang Ye 
 · · Organization(s): Wuhan University; Beijing Institute of Technology 
 · · Description: 
 · · Tags: distillation
 </details>
***
- Revisiting the Critical Factors of Augmentation-Invariant Representation Learning (**** - **ECCV**22) [[paper]](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910040.pdf) [[code]](https://github.com/megvii-research/revisitAIRL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Junqiang Huang, Xiangwen Kong, Xiangyu Zhang 
 · · Organization(s): MEGVII Technology 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Towards Efficient and Effective Self-Supervised Learning of Visual Representations (**EffSSL** - **ECCV**22) [[paper]](https://arxiv.org/abs/2210.09866) [[code]](https://github.com/val-iisc/EffSSL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Sravanti Addepalli, Kaushal Bhogale, Priyam Dey, R.Venkatesh Babu 
 · · Organization(s): Indian Institute of Science 
 · · Description: 
 · · Tags: 
 </details>
***
- Understanding Collapse in Non-Contrastive Siamese Representation Learning (**** - **ECCV**22) [[paper]](https://arxiv.org/abs/2209.15007) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Alexander C. Li, Alexei A. Efros, Deepak Pathakn 
 · · Organization(s): CMU; UCB 
 · · Description: 
 · · Tags: 
 </details>
***
- Masked Siamese Networks for Label-Efficient Learning (**MSN** - **ECCV**22) [[paper]](https://arxiv.org/abs/2204.07141) [[code]](https://github.com/facebookresearch/msn)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael Rabbat, Nicolas Ballas 
 · · Organization(s): Facebook AI Research; Mila – Quebec AI Institute; Inria, Univ. Grenoble Alpes; Universite de Montreal; McGill University 
 · · Description: 
 · · Tags: 
 </details>
***
- Decoupled Contrastive Learning (**DCL** - **ECCV**22) [[paper]](https://arxiv.org/abs/2110.06848) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Chun-Hsiao Yeh, Cheng-Yao Hong, Yen-Chi Hsu, Tyng-Luh Liu, Yubei Chen, Yann LeCun 
 · · Organization(s): IIS, Academia Sinica; UC Berkeley; National Taiwan University; Meta AI Research; New York University 
 · · Description: 
 · · Tags: 
 </details>
***
- Equivariance and Invariance Inductive Bias for
Learning from Insufficient Data (**EqInv** - **ECCV**22) [[paper]](https://arxiv.org/abs/2207.12258) [[code]](https://github.com/Wangt-CN/EqInv)
 <details>
 <summary>More Info</summary>
 · · Author(s): Tan Wang, Qianru Sun, Sugiri Pranata, Karlekar Jayashree, Hanwang Zhang 
 · · Organization(s): Nanyang Technological University; Singapore Management University; Panasonic R&D Center Singapore 
 · · Description: 
 · · Tags: 
 </details>
***
- Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches (**Fast-MoCo** - **ECCV**22) [[paper]](https://arxiv.org/abs/2207.08220) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Yuanzheng Ci, Chen Lin, Lei Bai, Wanli Ouyang 
 · · Organization(s): The University of Sydney; University of Oxford; Shanghai AI Laboratory 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Visual Representation Learning by Synchronous Momentum Grouping (**SMoG** - **ECCV**22) [[paper]](https://arxiv.org/abs/2207.06167) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Bo Pang, Yifan Zhang, Yaoyi Li, Jia Cai, Cewu Lu 
 · · Organization(s): Shanghai Jiao Tong University; HuaWei 
 · · Description: 
 · · Tags: Clustering, Contrastive Learning
 </details>
***
- Self-Supervision Can Be a Good Few-Shot Learner (**UniSiam** - **ECCV**22) [[paper]](https://arxiv.org/abs/2207.09176) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Yuning Lu, Liangjian Wen, Jianzhuang Liu, Yajing Liu, Xinmei Tian 
 · · Organization(s): University of Science and Technology of China; Huawei Noah’s Ark Lab; Hefei Comprehensive National Science Center 
 · · Description: 
 · · Tags: few-shot
 </details>
***
- ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images (**ConCL** - **ECCV**22) [[paper]](https://arxiv.org/abs/2207.06733) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Jiawei Yang, Hanbo Chen, Yuan Liang, Junzhou Huang, Lei He, Jianhua Yao 
 · · Organization(s): Tencent AI Lab; UCLA; University of Texas at Arlington 
 · · Description: 
 · · Tags: dense, medical
 </details>
***
- Dense Siamese Network for Dense Unsupervised Learning (**DenseSiam** - **ECCV**22) [[paper]](https://arxiv.org/abs/2203.11075) [[code]](https://github.com/ZwwWayne/DenseSiam)
 <details>
 <summary>More Info</summary>
 · · Author(s): Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy 
 · · Organization(s): Nanyang Technological University; Shanghai AI Laboratory; SenseTime Research 
 · · Description: 
 · · Tags: dense
 </details>
***
- Bootstrapped Masked Autoencoders for Vision BERT Pretraining (**BootMAE** - **ECCV**22) [[paper]](https://arxiv.org/abs/2207.07116) [[code]](https://github.com/LightDXY/BootMAE)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiaoyi Dong, Jianmin Bao, Ting Zhang, Dongdong Chen, Weiming Zhang, Lu Yuan, Dong Chen, Fang Wen, Nenghai Yu 
 · · Organization(s): University of Science and Technology of China; Microsoft Research Asia; Microsoft Cloud + AI 
 · · Description: 
 · · Tags: transformer
 </details>
***
- SdAE: Self-distillated Masked Autoencoder (**SdAE** - **ECCV**22) [[paper]](https://arxiv.org/abs/2208.00449) [[code]](https://github.com/AbrahamYabo/SdAE)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yabo Chen, Yuchen Liu, Dongsheng Jiang, Xiaopeng Zhang, Wenrui Dai, Hongkai Xiong, Qi Tian 
 · · Organization(s): Shanghai Jiao Tong University; Huawei Cloud EI 
 · · Description: 
 · · Tags: transformer
 </details>
***
- Contrastive Vision-Language Pre-training with Limited Resources (**ZeroVL** - **ECCV**22) [[paper]](https://arxiv.org/abs/2112.09331) [[code]](https://github.com/zerovl/ZeroVL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Quan Cui, Boyan Zhou, Yu Guo, Weidong Yin, Hao Wu, Osamu Yoshie, Yubo Chen 
 · · Organization(s): ByteDance; Waseda University 
 · · Description: 
 · · Tags: VL
 </details>
***
- Tailoring Self-Supervision for Supervised Learning (**LoRot** - **ECCV**22) [[paper]](https://arxiv.org/abs/2207.10023) [[code]](https://github.com/wjun0830/Localizable-Rotation)
 <details>
 <summary>More Info</summary>
 · · Author(s): WonJun Moon, Ji-Hwan Kim, Jae-Pil Heo 
 · · Organization(s): Sungkyunkwan University 
 · · Description: 
 · · Tags: supervised
 </details>
***
- DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning (**DisCo** - **ECCV**22 Oral) [[paper]](https://arxiv.org/abs/2104.09124) [[code]](https://github.com/Yuting-Gao/DisCo-pytorch)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yuting Gao, Jia-Xin Zhuang, Shaohui Lin, Hao Cheng, Xing Sun, Ke Li, Chunhua Shen 
 · · Organization(s): Tencent Youtu Lab; Hong Kong University of Science and Technology; East China Normal University; Zhejiang University 
 · · Description: 
 · · Tags: Self-supervised Distillation
 </details>

***
- Object discovery and representation networks (**Odin** - **ECCV**22) [[paper]](https://arxiv.org/abs/2203.08777)
 <details>
 <summary>More Info</summary>
 · · Author(s): Olivier J. Hénaff, Skanda Koppula, Evan Shelhamer, Daniel Zoran, Andrew Jaegle, Andrew Zisserman, João Carreira, Relja Arandjelović 
 · · Organization(s): TDeepMind 
 · · Description: 
 · · Tags: Dense
 </details>

***
- Position Prediction as an Effective Pretraining Strategy (**MP3** - **ICML**22) [[paper]](https://proceedings.mlr.press/v162/zhai22a/zhai22a.pdf) 
 <details> 
 <summary>More Info</summary>
 · · Author(s): Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram, Dan Busbridge, Tatiana Likhomanenko, Joseph Y Cheng, Walter Talbott, Chen Huang, Hanlin Goh, Joshua M Susskind 
 · · Organization(s): Apple Inc. 
 · · Description: 
 · · Tags: Transformer
 </details>

***
- Boosting Contrastive Learning with Relation Knowledge Distillation (**ReKD** - **AAAI**22) [[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/20262) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Kai Zheng, Yuanjiang Wang, Ye Yuan 
 · · Organization(s): Megvii Technology 
 · · Description: 
 · · Tags: distill
 </details>
***

- Masked Autoencoders Are Scalable Vision Learners (**MAE** - **CVPR**22 Oral) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/He_Masked_Autoencoders_Are_Scalable_Vision_Learners_CVPR_2022_paper.pdf) [[code]](https://github.com/facebookresearch/mae) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/He_Masked_Autoencoders_Are_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick 
 · · Organization(s): Facebook AI Research (FAIR) 
 · · Description: 
 · · Tags: Transformer
 </details>
***
- SimMIM: A Simple Framework for Masked Image Modeling (**SimMIM** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Xie_SimMIM_A_Simple_Framework_for_Masked_Image_Modeling_CVPR_2022_paper.pdf) [[code]](https://github.com/microsoft/SimMIM) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Xie_SimMIM_A_Simple_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu 
 · · Organization(s): Microsoft Research Asia 
 · · Description: 
 · · Tags: Transformer
 </details>
***
- Crafting Better Contrastive Views for Siamese Representation Learning (**ContrastiveCrop** - **CVPR**22 Oral) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Peng_Crafting_Better_Contrastive_Views_for_Siamese_Representation_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/xyupeng/ContrastiveCrop)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiangyu Peng, Kai Wang, Zheng Zhu, Mang Wang, Yang You 
 · · Organization(s): National University of Singapore; Tsinghua University; Alibaba Group 
 · · Description: 
 · · Tags: 
 </details>
***
- A Simple Data Mixing Prior for Improving Self-Supervised Learning (**SDMP** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Ren_A_Simple_Data_Mixing_Prior_for_Improving_Self-Supervised_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/OliverRensu/SDMP)
 <details>
 <summary>More Info</summary>
 · · Author(s): Sucheng Ren, Huiyu Wang, Zhengqi Gao, Shengfeng He, Alan Yuille, Yuyin Zhou, Cihang Xie 
 · · Organization(s): South China University of Technology; Johns Hopkins University; Massachusetts Institute of Technology; UC Santa Cruz 
 · · Description: 
 · · Tags: Interpolation
 </details>
***
- On the Importance of Asymmetry for Siamese Representation Learning (**asym-siam** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_On_the_Importance_of_Asymmetry_for_Siamese_Representation_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/facebookresearch/asym-siam) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Wang_On_the_Importance_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiao Wang, Haoqi Fan, Yuandong Tian, Daisuke Kihara, Xinlei Chen 
 · · Organization(s): Facebook AI Research (FAIR); Purdue University 
 · · Description: 
 · · Tags: 
 </details>
***
- HCSC: Hierarchical Contrastive Selective Coding (**HCSC** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Guo_HCSC_Hierarchical_Contrastive_Selective_Coding_CVPR_2022_paper.pdf) [[code]](https://github.com/gyfastas/HCSC) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Guo_HCSC_Hierarchical_Contrastive_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yuanfan Guo, Minghao Xu, Jiawen Li, Bingbing Ni, Xuanyu Zhu, Zhenbang Sun, Yi Xu 
 · · Organization(s): MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University; 2Mila - Qu´ebec AI Institute, University of Montr´eal; ByteDance 
 · · Description: 
 · · Tags: Clustering
 </details>
***
- Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning (**BURN** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Kim_Unsupervised_Representation_Learning_for_Binary_Networks_by_Joint_Classifier_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/naver-ai/burn) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Kim_Unsupervised_Representation_Learning_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Dahyun Kim, Jonghyun Choi 
 · · Organization(s): Upstage AI Research; NAVER AI Lab.; Yonsei University 
 · · Description: 
 · · Tags: 
 </details>
***
- Unleashing Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification (**UP-ReID** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_Unleashing_Potential_of_Unsupervised_Pre-Training_With_Intra-Identity_Regularization_for_Person_CVPR_2022_paper.pdf) [[code]](https://github.com/Frost-Yang-99/UP-ReID) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Yang_Unleashing_Potential_of_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao 
 · · Organization(s): University of Science and Technology of China 
 · · Description: 
 · · Tags: 
 </details>
***
- UniVIP: A Unified Framework for Self-Supervised Visual Pre-training (**UniVIP** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Li_UniVIP_A_Unified_Framework_for_Self-Supervised_Visual_Pre-Training_CVPR_2022_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhaowen Li, Yousong Zhu, Fan Yang, Wei Li, Chaoyang Zhao, Yingying Chen, Zhiyang Chen, Jiahao Xie, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang 
 · · Organization(s): National Laboratory of Pattern Recognition, Institute of Automation, CAS; School of Artificial Intelligence, University of Chinese Academy of Sciences; SenseTime Research; etc. 
 · · Description: 
 · · Tags: 
 </details>
***
- Semantic-Aware Auto-Encoders for Self-supervised Representation Learning (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_Semantic-Aware_Auto-Encoders_for_Self-Supervised_Representation_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/wanggrun/Semantic-Aware-AE)
 <details>
 <summary>More Info</summary>
 · · Author(s): Guangrun Wang, Yansong Tang, Liang Lin, Philip H.S. Torr 
 · · Organization(s): University of Oxford; Tsinghua-Berkeley Shenzhen Institute, Tsinghua University; Sun Yat-sen University 
 · · Description: 
 · · Tags: 
 </details>
***
- Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhang_Rethinking_the_Augmentation_Module_in_Contrastive_Learning_Learning_Hierarchical_Augmentation_CVPR_2022_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Junbo Zhang, Kaisheng Ma 
 · · Organization(s): Tsinghua University 
 · · Description: 
 · · Tags: 
 </details>
***
- Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy (**LoGo** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhang_Leverage_Your_Local_and_Global_Representations_A_New_Self-Supervised_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/ztt1024/LoGo-SSL) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Zhang_Leverage_Your_Local_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Tong Zhang, Congpei Qiu, Wei Ke, Sabine Süsstrunk, Mathieu Salzmann 
 · · Organization(s): School of Computer and Communication Sciences, EPFL; Xi’an Jiaotong University 
 · · Description: 
 · · Tags: 
 </details>
***
- Learning Where to Learn in Cross-View Self-Supervised Learning (**LEWEL** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Huang_Learning_Where_To_Learn_in_Cross-View_Self-Supervised_Learning_CVPR_2022_paper.pdf) [[code]](https://t.ly/ZI0A) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Huang_Learning_Where_To_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Lang Huang, Shan You, Mingkai Zheng, Fei Wang, Chen Qian, Toshihiko Yamasaki 
 · · Organization(s): The University of Tokyo; SenseTime Research; The University of Sydney 
 · · Description: 
 · · Tags: 
 </details>
***
- Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Tao_Exploring_the_Equivalence_of_Siamese_Self-Supervised_Learning_via_a_Unified_CVPR_2022_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Tao_Exploring_the_Equivalence_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Chenxin Tao, Honghui Wang, Xizhou Zhu, Jiahua Dong, Shiji Song, Gao Huang, Jifeng Dai 
 · · Organization(s): Tsinghua University; SenseTime Research; Zhejiang University; Beijing Academy of Artificial Intelligence 
 · · Description: 
 · · Tags: 
 </details>
***
- Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo (**DT** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhang_Dual_Temperature_Helps_Contrastive_Learning_Without_Many_Negative_Samples_Towards_CVPR_2022_paper.pdf) [[code]](https://github.com/ChaoningZhang/Dual-temperature) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Zhang_Dual_Temperature_Helps_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Chaoning Zhang, Kang Zhang, Trung X. Pham, Axi Niu, Zhinan Qiao, Chang D. Yoo, In So Kweon 
 · · Organization(s): KAIST; Northwestern Polytechnical University; University of North Texas 
 · · Description: 
 · · Tags: 
 </details>
***
- Directional Self-supervised Learning for Heavy Image Augmentations (**DSSL** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Bai_Directional_Self-Supervised_Learning_for_Heavy_Image_Augmentations_CVPR_2022_paper.pdf) [[code]](https://github.com/Yif-Yang/DSSL) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Bai_Directional_Self-Supervised_Learning_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yalong Bai, Yifan Yang, Wei Zhang, Tao Mei 
 · · Organization(s): JD AI Research; Peking University 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Visual Representation Learning by Online Constrained K-Means (**CoKe** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Qian_Unsupervised_Visual_Representation_Learning_by_Online_Constrained_K-Means_CVPR_2022_paper.pdf) [[code]](https://github.com/idstcv/CoKe) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Qian_Unsupervised_Visual_Representation_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Qi Qian, Yuanhong Xu, Juhua Hu, Hao Li, Rong Jin 
 · · Organization(s): Alibaba Group, Bellevue; Alibaba Group, Hangzhou; University of Washington 
 · · Description: 
 · · Tags: 
 </details>
***
- Align Representations with Base: A New Approach to Self-Supervised Learning (**ARB** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhang_Align_Representations_With_Base_A_New_Approach_to_Self-Supervised_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/Sherrylone/Align-Representation-with-Base)
 <details>
 <summary>More Info</summary>
 · · Author(s): Shaofeng Zhang, Lyn Qiu, Feng Zhu, Junchi Yan, Hengrui Zhang, Rui Zhao, Hongyang Li, Xiaokang Yang 
 · · Organization(s): Shanghai Jiao Tong University; SenseTime Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Exploring Set Similarity for Dense Self-supervised Representation Learning (**SetSim** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhang_Align_Representations_With_Base_A_New_Approach_to_Self-Supervised_Learning_CVPR_2022_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Shaofeng Zhang, Lyn Qiu, Feng Zhu, Junchi Yan, Hengrui Zhang, Rui Zhao, Hongyang Li, Xiaokang Yang 
 · · Organization(s): University of Sydney; Kuaishou Technology; Xidian University; University of Melbourne 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- Patch-level Representation Learning for Self-supervised Vision Transformers (**SelfPatch** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Yun_Patch-Level_Representation_Learning_for_Self-Supervised_Vision_Transformers_CVPR_2022_paper.pdf) [[code]](https://github.com/alinlab/SelfPatch) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Yun_Patch-Level_Representation_Learning_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Sukmin Yun, Hankook Lee, Jaehyung Kim, Jinwoo Shin 
 · · Organization(s): Korea Advanced Institute of Science and Technology (KAIST) 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- Self-Supervised Learning of Object Parts for Semantic Segmentation (**Leopart** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Ziegler_Self-Supervised_Learning_of_Object_Parts_for_Semantic_Segmentation_CVPR_2022_paper.pdf) [[~~No code~~]]( https://github.com/MkuuWaUjinga/leopart) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Ziegler_Self-Supervised_Learning_of_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Adrian Ziegler, Yuki M. Asano 
 · · Organization(s): Technical University of Munich; QUVA Lab, University of Amsterdam 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- Point-Level Region Contrast for Object Detection Pre-Training (**** - **CVPR**22 Oral) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Bai_Point-Level_Region_Contrast_for_Object_Detection_Pre-Training_CVPR_2022_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Bai_Point-Level_Region_Contrast_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yutong Bai, Xinlei Chen, Alexander Kirillov, Alan Yuille, Alexander C. Berg 
 · · Organization(s): Facebook AI Research (FAIR); Johns Hopkins University 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- Use All The Labels: A Hierarchical Multi-Label Contrastive Learning (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhang_Use_All_the_Labels_A_Hierarchical_Multi-Label_Contrastive_Learning_Framework_CVPR_2022_paper.pdf) [[code]](https://github.com/salesforce/hierarchicalContrastiveLearning) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Zhang_Use_All_the_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Shu Zhang, Ran Xu, Caiming Xiong, Chetan Ramaiah 
 · · Organization(s): Salesforce Research 
 · · Description: 
 · · Tags: Label supervision
 </details>
***
- Revisiting the Transferability of Supervised Pretraining: an MLP Perspective (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_Revisiting_the_Transferability_of_Supervised_Pretraining_An_MLP_Perspective_CVPR_2022_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Wang_Revisiting_the_Transferability_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang 
 · · Organization(s): Zhejiang University; The University of Sydney; SenseTime Research; Shanghai Jiao Tong University 
 · · Description: 
 · · Tags: Label supervision
 </details>
***
- Does Robustness on ImageNet Transfer to Downstream Tasks? (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Yamada_Does_Robustness_on_ImageNet_Transfer_to_Downstream_Tasks_CVPR_2022_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Yamada_Does_Robustness_on_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yutaro Yamada, Mayu Otani 
 · · Organization(s): Yale University; CyberAgent, Inc. 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- When Does Contrastive Visual Representation Learning Work? (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Cole_When_Does_Contrastive_Visual_Representation_Learning_Work_CVPR_2022_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Elijah Cole, Xuan Yang, Kimberly Wilber, Oisin Mac Aodha, Serge Belongie 
 · · Organization(s): Caltech; Google; University of Edinburgh; Alan Turing Institute; University of Copenhagen 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Rethinking Minimal Sufficient Representation in Contrastive Learning (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_Rethinking_Minimal_Sufficient_Representation_in_Contrastive_Learning_CVPR_2022_paper.pdf) [[code]](https://github.com/Haoqing-Wang/InfoCL) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Wang_Rethinking_Minimal_Sufficient_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Haoqing Wang, Xun Guo, Zhi-Hong Deng, Yan Lu 
 · · Organization(s): Peking University; Microsoft Research Asia 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning (**** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Gwilliam_Beyond_Supervised_vs._Unsupervised_Representative_Benchmarking_and_Analysis_of_Image_CVPR_2022_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Gwilliam_Beyond_Supervised_vs._CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Matthew Gwilliam, Abhinav Shrivastava 
 · · Organization(s): University of Maryland, College Park 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- DETReg: Unsupervised Pretraining with
Region Priors for Object Detection (**DETReg** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Bar_DETReg_Unsupervised_Pretraining_With_Region_Priors_for_Object_Detection_CVPR_2022_paper.pdf) [[code]](https://www.amirbar.net/detreg/) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Bar_DETReg_Unsupervised_Pretraining_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Amir Bar, Xin Wang, Vadim Kantorov, Colorado J. Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson 
 · · Organization(s): Tel-Aviv University; Berkeley AI Research; NVIDIA; Bar-Ilan University; Microsoft Research 
 · · Description: 
 · · Tags: Transformer
 </details>
***
- Masked Feature Prediction for Self-Supervised Visual Pre-Training (**MaskFeat** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Wei_Masked_Feature_Prediction_for_Self-Supervised_Visual_Pre-Training_CVPR_2022_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Wei_Masked_Feature_Prediction_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Chen Wei, Haoqi Fan, Saining Xie, Chao-Yuan Wu, Alan Yuille, Christoph Feichtenhofer 
 · · Organization(s): Facebook AI Research; Johns Hopkins University 
 · · Description: 
 · · Tags: Transformer
 </details>
***
- Self-Taught Metric Learning without Labels (**STML** - **CVPR**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Kim_Self-Taught_Metric_Learning_Without_Labels_CVPR_2022_paper.pdf) [[code]](https://github.com/tjddus9597/STML-CVPR22) [[supp]](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Kim_Self-Taught_Metric_Learning_CVPR_2022_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Sungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak 
 · · Organization(s): FDept. of CSE, POSTECH; Graduate School of AI, POSTECH 
 · · Description: 
 · · Tags: 
 </details>
***
- CoDo: Contrastive Learning with Downstream Background Invariance for Detection (**CoDo** - **CVPRW**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022W/L3D-IVU/papers/Zhao_CoDo_Contrastive_Learning_With_Downstream_Background_Invariance_for_Detection_CVPRW_2022_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Bing Zhao, Jun Li, Hong Zhu 
 · · Organization(s): Department of AI and HPC Inspur Electronic Information Industry Co., Ltd 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- What Should Be Equivariant In Self-Supervised Learning (**** - **CVPRW**22) [[paper]](https://openaccess.thecvf.com/content/CVPR2022W/L3D-IVU/papers/Xie_What_Should_Be_Equivariant_in_Self-Supervised_Learning_CVPRW_2022_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Yuyang Xie, Jianhong Wen, Kin Wai Lau, Yasar Abbas Ur Rehman, Jiajun Shen 
 · · Organization(s): TCL AI Lab; Fuzhou University; City University of Hong Kong 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer (**** - **CVPRW**22?) [[paper]](https://arxiv.org/abs/2206.00481) [[code]](https://github.com/guglielmocamporese/relvit)
 <details>
 <summary>More Info</summary>
 · · Author(s): Guglielmo Camporese, Elena Izzo, Lamberto Ballan 
 · · Organization(s): University of Padova, Italy 
 · · Description: 
 · · Tags: 
 </details>
***
- Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors (**DUPR** - **TPAMI**22) [[paper]](https://ieeexplore.ieee.org/document/9749837) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Jian Ding, Enze Xie, Hang Xu, Chenhan Jiang, Zhenguo Li, Ping Luo, Guidong Xia 
 · · Organization(s): Wuhan University; Huawei Noah’s Ark Lab; University of Hong Kong 
 · · Description: 
 · · Tags: 
 </details>
***
- Learning Generalized Transformation Equivariant Representations Via AutoEncoding Transformations (**** - **TPAMI**22) [[paper]](https://ieeexplore.ieee.org/document/9219238) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Guo-Jun Qi, Liheng Zhang, Feng Lin, Xiao Wang 
 · · Organization(s): Futurewei Seattle Cloud Lab; University of Central Florida; University of Science and Technology of China; Purdue University 
 · · Description: 
 · · Tags: 
 </details>

## 2021

***
- Improving Transformation Invariance in Contrastive Representation Learning (**InvCLR** - **ICLR**21) [[paper]](https://openreview.net/forum?id=NomEDgIEBwE) [[code]](https://github.com/ae-foster/invclr)
 <details>
 <summary>More Info</summary>
 · · Author(s): Adam Foster, Rattana Pukdee, Tom Rainforth 
 · · Organization(s): University of Oxford 
 · · Description: 
 · · Tags: 
 </details>
***
- Contrastive Learning with Hard Negative Samples (**HCL** - **ICLR**21) [[paper]](https://openreview.net/forum?id=CR1XOQ0UTh-) [[code]](https://github.com/joshr17/HCL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Joshua David Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka 
 · · Organization(s): Massachusetts Institute of Technology 
 · · Description: 
 · · Tags: Hard negative
 </details>
***
- Representation Learning via Invariant Causal Mechanisms (**ReLIC** - **ICLR**21) [[paper]](https://openreview.net/forum?id=9p2ekP904Rs) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Jovana Mitrovic, Brian McWilliams, Jacob C Walker, Lars Holger Buesing, Charles Blundell 
 · · Organization(s): DeepMind 
 · · Description: 
 · · Tags: Analysis, Distribution
 </details>
***
- i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning (**i-Mix** - **ICLR**21) [[paper]](https://openreview.net/forum?id=T6AxtOaWydQ) [[code]](https://github.com/kibok90/imix)
 <details>
 <summary>More Info</summary>
 · · Author(s): Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee 
 · · Organization(s): University of Michigan; Amazon Web Services; Google Cloud AI; KAIST; LG AI Research 
 · · Description: 
 · · Tags: Interpolation
 </details>
***
- What Should Not Be Contrastive in Contrastive Learning (**LooC** - **ICLR**21) [[paper]](https://openreview.net/forum?id=CZ8Y3NzuVzO) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Tete Xiao, Xiaolong Wang, Alexei A Efros, Trevor Darrell 
 · · Organization(s): UC Berkeley; UC San Diego 
 · · Description: 
 · · Tags: 
 </details>
***
- CO2: Consistent Contrast for Unsupervised Visual Representation Learning (**CO2** - **ICLR**21) [[paper]](https://openreview.net/forum?id=U4XLJhqwNF1) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Chen Wei, Huiyu Wang, Wei Shen, Alan Yuille 
 · · Organization(s): Johns Hopkins University 
 · · Description: 
 · · Tags: Distribution
 </details>
***
- What Makes Instance Discrimination Good for Transfer Learning? (**** - **ICLR**21) [[paper]](https://openreview.net/forum?id=tC6iW2UUbJf) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Nanxuan Zhao, Zhirong Wu, Rynson W. H. Lau, Stephen Lin 
 · · Organization(s): City University of Hong Kong; Microsoft Research Asia 
 · · Description: 
 · · Tags: Transfer
 </details>
***
- SEED: Self-supervised Distillation For Visual Representation (**SEED** - **ICLR**21) [[paper]](https://openreview.net/forum?id=AHm3dbp7D1D) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhiyuan Fang, Jianfeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang, Zicheng Liu 
 · · Organization(s): Arizona State University; Microsoft Corporation 
 · · Description: 
 · · Tags: Self-supervised distillation
 </details>
***
- Prototypical Contrastive Learning of Unsupervised Representations (**PCL** - **ICLR**21) [[paper]](https://openreview.net/forum?id=KmykpuSrjcq) [[code]](https://github.com/salesforce/PCL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Junnan Li, Pan Zhou, Caiming Xiong, Steven Hoi 
 · · Organization(s): Salesforce Research 
 · · Description: 
 · · Tags: Clustering
 </details>

***
- Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly (**OSS** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/cecd845e3577efdaaf24eea03af4c033-Abstract.html) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Hee Min Choi, Hyoa Kang, Dokwan Oh 
 · · Organization(s): Samsung Advanced Institute of Technology 
 · · Description: 
 · · Tags: distill
 </details>

***
- Aligning Pretraining for Detection via Object-Level Contrastive Learning (**SoCo** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/bf5cd8b2509011b9502a72296edc14a0-Abstract.html) [[code]](https://github.com/hologerry/SoCo)
 <details>
 <summary>More Info</summary>
 · · Author(s): Fangyun Wei, Yue Gao, Zhirong Wu, Han Hu, Stephen Lin 
 · · Organization(s): Microsoft Research Asia 
 · · Description: 
 · · Tags: local
 </details>
***
- Unsupervised Object-Level Representation Learning
from Scene Images (**ORL** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/f1b6f2857fb6d44dd73c7041e0aa0f19-Abstract.html) [[code]](https://www.mmlab-ntu.com/project/orl/)
 <details>
 <summary>More Info</summary>
 · · Author(s): Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy 
 · · Organization(s): Nanyang Technological University; The Chinese University of Hong Kong 
 · · Description: 
 · · Tags: local
 </details>
***
- Object-aware Contrastive Learning for Debiased Scene Representation (**ContraCAM** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/65d2ea03425887a717c435081cfc5dbb-Abstract.html) [[code]](https://github.com/alinlab/object-aware-contrastive)
 <details>
 <summary>More Info</summary>
 · · Author(s): Sangwoo Mo, Hyunwoo Kang, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin 
 · · Organization(s): KAIST; Google Cloud AI 
 · · Description: 
 · · Tags: contextual bias
 </details>
***
- Intriguing Properties of Contrastive Losses (**** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/628f16b29939d1b060af49f66ae0f7f8-Abstract.html) [[code]](https://contrastive-learning.github.io/intriguing)
 <details>
 <summary>More Info</summary>
 · · Author(s): Ting Chen, Calvin Luo, Lala Li 
 · · Organization(s): Google Research 
 · · Description: 
 · · Tags: 
 </details>
***
- ReSSL: Relational Self-Supervised Learning with Weak Augmentation (**ReSSL** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/14c4f36143b4b09cbc320d7c95a50ee7-Abstract.html) [[code]](https://github.com/KyleZheng1997/ReSSL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mingkai Zheng, Shan You, Fei Wang, Chen Qian, Changshui Zhang, Xiaogang Wang, Chang Xu 
 · · Organization(s): SenseTime Research; Tsinghua University; The Chinese University of Hong Kong; The University of Sydney 
 · · Description: 
 · · Tags: 
 </details>

***
- Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning (**CARE** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/21be992eb8016e541a15953eee90760e-Abstract.html) [[code]](https://github.com/ChongjianGE/CARE)
 <details>
 <summary>More Info</summary>
 · · Author(s): Chongjian GE, Youwei Liang, YIBING SONG, Jianbo Jiao, Jue Wang, Ping Luo 
 · · Organization(s): The University of Hong Kong; Tencent AI Lab; University of Oxford 
 · · Description: 
 · · Tags: 
 </details>

***
- Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss (**** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/27debb435021eb68b3965290b5e24c49-Abstract.html)
 <details>
 <summary>More Info</summary>
 · · Author(s): Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma 
 · · Organization(s): Stanford University; Toyota Research Institute 
 · · Description: 
 · · Tags: 
 </details>

***
- Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration (**UOTA** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/e8855b3528cb03d1def9803220bd3cb9-Abstract.html)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yu Wang, Jingyang Lin, Jingjing Zou, Yingwei Pan, Ting Yao, Tao Mei 
 · · Organization(s): JD AI Research; Sun Yat-sen University; University of California, San Diego 
 · · Description: 
 · · Tags: 
 </details>
***
- Compressive Visual Representations (**** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/hash/a29a5ba2cb7bdeabba22de8c83321b46-Abstract.html)
 <details>
 <summary>More Info</summary>
 · · Author(s): Kuang-Huei Lee, Anurag Arnab, Sergio Guadarrama, John Canny, Ian Fischer 
 · · Organization(s): Google Research 
 · · Description: 
 · · Tags: Compress
 </details>

***
- MST: Masked Self-Supervised Transformer for Visual Representation (**MST** - **NeurIPS**21) [[paper]](https://proceedings.neurips.cc/paper/2021/file/6dbbe6abe5f14af882ff977fc3f35501-Paper.pdf) [[supp]](https://proceedings.neurips.cc/paper/2021/file/6dbbe6abe5f14af882ff977fc3f35501-Supplemental.zip)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhaowen Li, Zhiyang Chen, Fan Yang, Wei Li, Yousong Zhu, Chaoyang Zhao, Rui Deng, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang 
 · · Organization(s): Institute of Automation, CAS; UCAS; SenseTime Research; UCLA 
 · · Description: 
 · · Tags: Transformer, MIM
 </details>

***
- Exploring Simple Siamese Representation Learning (**SimSiam** - **CVPR**21 Oral) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_Exploring_Simple_Siamese_Representation_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/facebookresearch/simsiam) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Chen_Exploring_Simple_Siamese_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xinlei Chen, Kaiming He 
 · · Organization(s): Facebook AI Research (FAIR) 
 · · Description: 
 · · Tags: Siamese architecture
 </details>
***
- Jigsaw Clustering for Unsupervised Visual Representation Learning (**JigClu** - **CVPR**21 Oral) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_Jigsaw_Clustering_for_Unsupervised_Visual_Representation_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/Jia-Research-Lab/JigsawClustering) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Chen_Jigsaw_Clustering_for_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Pengguang Chen, Shu Liu, Jiaya Jia 
 · · Organization(s): The Chinese University of Hong Kong; SmartMore 
 · · Description: 
 · · Tags: Single branch
 </details>
***
- OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning (**OBoW** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Gidaris_OBoW_Online_Bag-of-Visual-Words_Generation_for_Self-Supervised_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/valeoai/obow) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Gidaris_OBoW_Online_Bag-of-Visual-Words_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Perez 
 · · Organization(s): valeo.ai; University of Crete; Sorbonne Université 
 · · Description: 
 · · Tags: 
 </details>
***
- Spatial Assembly Networks for Image Representation Learning (**SAN** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Spatial_Assembly_Networks_for_Image_Representation_Learning_CVPR_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Li_Spatial_Assembly_Networks_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yang Li, Shichao Kan, Jianhe Yuan, Wenming Cao, Zhihai He 
 · · Organization(s): University of Missouri, MO; Beijing Jiaotong University; Shenzhen University 
 · · Description: 
 · · Tags: 
 </details>
***
- SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning (**SelfAugment** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Reed_SelfAugment_Automatic_Augmentation_Policies_for_Self-Supervised_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/cjrd/selfaugment) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Reed_SelfAugment_Automatic_Augmentation_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Colorado J Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell, Kurt Keutzer 
 · · Organization(s): BAIR, Department of Computer Science, UC Berkeley; Graduate Group in Bioengineering (Berkeley/UCSF), Weill Neurosciences Institute & UCSF Neurological Surgery 
 · · Description: 
 · · Tags: 
 </details>
***
- Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement (**PSL** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Progressive_Stage-Wise_Learning_for_Unsupervised_Feature_Representation_Enhancement_CVPR_2021_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Zefan Li, Chenxi Liu, Alan Yuille, Bingbing Ni, Wenjun Zhang, Wen Gao 
 · · Organization(s): Shanghai Jiao Tong University; Johns Hopkins University; Peking University; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Pre-training for Person Re-identification (**** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Fu_Unsupervised_Pre-Training_for_Person_Re-Identification_CVPR_2021_paper.pdf) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Dengpan Fu, Dongdong Chen, Jianmin Bao, Hao Yang, Lu Yuan, Lei Zhang, Houqiang Li, Dong Chen 
 · · Organization(s): University of Science and Technology of China; Microsoft Research 
 · · Description: 
 · · Tags: Dataset
 </details>
***
- Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning (**PixPro** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Xie_Propagate_Yourself_Exploring_Pixel-Level_Consistency_for_Unsupervised_Visual_Representation_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/zdaxie/PixPro)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhenda Xie, Yutong Lin, Zheng Zhang, Yue Cao, Stephen Lin, Han Hu 
 · · Organization(s): Tsinghua University; Xi’an Jiaotong University; Microsoft Research Asia 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- How Well Do Self-Supervised Models Transfer? (**** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Ericsson_How_Well_Do_Self-Supervised_Models_Transfer_CVPR_2021_paper.pdf) [[code]](https://github.com/linusericsson/ssl-transfer) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Ericsson_How_Well_Do_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Linus Ericsson, Henry Gouk, Timothy M. Hospedales 
 · · Organization(s): University of Edinburgh; Samsung AI Research, Cambridge 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning (**EMAN** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Cai_Exponential_Moving_Average_Normalization_for_Self-Supervised_and_Semi-Supervised_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/amazon-research/exponential-moving-average-normalization) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Cai_Exponential_Moving_Average_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhaowei Cai, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Zhuowen Tu, Stefano Soatto 
 · · Organization(s): Amazon Web Services 
 · · Description: 
 · · Tags: 
 </details>
***
- Dense Contrastive Learning for Self-Supervised Visual Pre-Training (**DenseCL** - **CVPR**21 Oral) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Dense_Contrastive_Learning_for_Self-Supervised_Visual_Pre-Training_CVPR_2021_paper.pdf) [[code]](https://github.com/WXinlong/DenseCL) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Wang_Dense_Contrastive_Learning_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li 
 · · Organization(s): The University of Adelaide; Tongji University; ByteDance AI Lab 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination (**CLD** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Unsupervised_Feature_Learning_by_Cross-Level_Instance-Group_Discrimination_CVPR_2021_paper.pdf) [[code]]( https://github.com/frankxwang/CLD-UnsupervisedLearning) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Wang_Unsupervised_Feature_Learning_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xudong Wang, Ziwei Liu, Stella X. Yu 
 · · Organization(s): UC Berkeley / ICSI; S-Lab, NTU 
 · · Description: 
 · · Tags: 
 </details>
***
- AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries (**AdCo** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Hu_AdCo_Adversarial_Contrast_for_Efficient_Learning_of_Unsupervised_Representations_From_CVPR_2021_paper.pdf) [[code]](https://github.com/maple-research-lab/AdCo) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Hu_AdCo_Adversarial_Contrast_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Qianjiang Hu, Xiao Wang, Wei Hu, Guo-Jun Qi 
 · · Organization(s): Peking University; Purdue University; Laboratory for MAchine Perception and LEarning (MAPLE) 
 · · Description: 
 · · Tags: 
 </details>
***
- CASTing Your Model: Learning to Localize Improves Self-Supervised Representations (**CAST** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Selvaraju_CASTing_Your_Model_Learning_To_Localize_Improves_Self-Supervised_Representations_CVPR_2021_paper.pdf) [[code]](https://github.com/salesforce/CAST) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Selvaraju_CASTing_Your_Model_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Ramprasaath R. Selvaraju, Karan Desai, Justin Johnson, Nikhil Naik 
 · · Organization(s): Salesforce Research; University of Michigan 
 · · Description: 
 · · Tags: 
 </details>
***
- Instance Localization for Self-supervised Detection Pretraining (**InsLoc** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Yang_Instance_Localization_for_Self-Supervised_Detection_Pretraining_CVPR_2021_paper.pdf) [[code]](https://github.com/limbo0000/InstanceLoc) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Ceyuan Yang, Zhirong Wu, Bolei Zhou, Stephen Lin 
 · · Organization(s): Chinese University of Hong Kong; Microsoft Research Asia 
 · · Description: 
 · · Tags: 
 </details>
***
- PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering (**PiCIE** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Cho_PiCIE_Unsupervised_Semantic_Segmentation_Using_Invariance_and_Equivariance_in_Clustering_CVPR_2021_paper.pdf) [[code]](https://github.com/janghyuncho/PiCIE) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Cho_PiCIE_Unsupervised_Semantic_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Jang Hyun Cho, Utkarsh Mall, Kavita Bala, Bharath Hariharan 
 · · Organization(s): University of Texas at Austin; Cornell University 
 · · Description: 
 · · Tags: Unsupervised semantic segmentation
 </details>
***
- Self-supervised Augmentation Consistency for Adapting Semantic Segmentation (**SAC** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Araslanov_Self-Supervised_Augmentation_Consistency_for_Adapting_Semantic_Segmentation_CVPR_2021_paper.pdf) [[code]](https://github.com/visinf/da-sac) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Araslanov_Self-Supervised_Augmentation_Consistency_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Nikita Araslanov, Stefan Roth 
 · · Organization(s): Department of Computer Science, TU Darmstadt; hessian.AI 
 · · Description: 
 · · Tags: Domain adaptation
 </details>
***
- Spatially Consistent Representation Learning (**SCRL** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Roh_Spatially_Consistent_Representation_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/kakaobrain/scrl) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Roh_Spatially_Consistent_Representation_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Byungseok Roh, Wuhyun Shin, Ildoo Kim, Sungwoong Kim 
 · · Organization(s): Kakao Brain 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- UP-DETR: Unsupervised Pre-training for Object Detection with Transformers (**UP-DETR** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Dai_UP-DETR_Unsupervised_Pre-Training_for_Object_Detection_With_Transformers_CVPR_2021_paper.pdf) [[code]](https://github.com/dddzg/up-detr) [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Dai_UP-DETR_Unsupervised_Pre-Training_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhigang Dai, Bolun Cai, Yugeng Lin, Junying Chen 
 · · Organization(s): School of Software Engineering, South China University of Technology; Tencent Wechat AI; Key Laboratory of Big Data and Intelligent Robot 
 · · Description: 
 · · Tags: 
 </details>
***
- Understanding the Behaviour of Contrastive Loss (**** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Understanding_the_Behaviour_of_Contrastive_Loss_CVPR_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Wang_Understanding_the_Behaviour_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Feng Wang, Huaping Liu 
 · · Organization(s): Beijing National Research Center for Information Science and Technology(BNRist), Department of Computer Science and Technology, Tsinghua University 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Unsupervised Hyperbolic Metric Learning (**** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Yan_Unsupervised_Hyperbolic_Metric_Learning_CVPR_2021_paper.pdf) [[code]](https://github.com/JiexiYan/UnHyperML) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Jiexi Yan, Lei Luo, Cheng Deng, Heng Huang 
 · · Organization(s): Xidian University; University of Pittsburgh; JD Finance America Corporation, Mountain View 
 · · Description: 
 · · Tags: Metric Learning
 </details>
***
- Relative Order Analysis and Optimization for Unsupervised Deep Metric Learning (**ROUL** - **CVPR**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Kan_Relative_Order_Analysis_and_Optimization_for_Unsupervised_Deep_Metric_Learning_CVPR_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/CVPR2021/supplemental/Kan_Relative_Order_Analysis_CVPR_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Shichao Kan, Yigang Cen, Yang Li, Vladimir Mladenovic, Zhihai He 
 · · Organization(s): Beijing Jiaotong University; Beijing Key Laboratory of Advanced Information Science and Network Technology; University of Missouri; Faculty of Technical Sciences University of Kragujevac 
 · · Description: 
 · · Tags: Metric Learning
 </details>

***
- Distill on the Go: Online Knowledge Distillation in Self-Supervised Learning (**DoGo** - **CVPRW**21) [[paper]](https://openaccess.thecvf.com/content/CVPR2021W/LLID/html/Bhat_Distill_on_the_Go_Online_Knowledge_Distillation_in_Self-Supervised_Learning_CVPRW_2021_paper.html) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Prashant Bhat, Elahe Arani, Bahram Zonooz 
 · · Organization(s): Advanced Research Lab, NavInfo Europe, Eindhoven, The Netherlands 
 · · Description: 
 · · Tags: distill
 </details>
 
***
- DetCo: Unsupervised Contrastive Learning for Object Detection (**DetCo** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Xie_DetCo_Unsupervised_Contrastive_Learning_for_Object_Detection_ICCV_2021_paper.pdf) [[code]](github.com/xieenze/DetCo) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Xie_DetCo_Unsupervised_Contrastive_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Enze Xie, Jian Ding, Wenhai Wang, Xiaohang Zhan, Hang Xu, Peize Sun, Zhenguo Li, Ping Luo 
 · · Organization(s): The University of Hong Kong; Huawei Noah’s Ark Lab; Wuhan University; Nanjing University; Chinese University of Hong Kong 
 · · Description: 
 · · Tags: 
 </details>
***
- Divide and Contrast: Self-supervised Learning from Uncurated Data (**DnC** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Tian_Divide_and_Contrast_Self-Supervised_Learning_From_Uncurated_Data_ICCV_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Tian_Divide_and_Contrast_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yonglong Tian, Olivier J. Hénaff, Aäron van den Oord 
 · · Organization(s): MIT; DeepMind 
 · · Description: 
 · · Tags: Uncurated data
 </details>
***
- Improve Unsupervised Pretraining for Few-label Transfer (**** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Li_Improve_Unsupervised_Pretraining_for_Few-Label_Transfer_ICCV_2021_paper.pdf) [[~~No code~~]]() 
 <details>
 <summary>More Info</summary>
 · · Author(s): Suichan Li, Dongdong Chen, Yinpeng Chen, Lu Yuan, Lei Zhang, Qi Chu, Bin Liu, Nenghai Yu 
 · · Organization(s): University of Science and Technology of China; Microsoft Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Visual Representations Learning by Contrastive Mask Prediction (**MaskCo** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhao_Self-Supervised_Visual_Representations_Learning_by_Contrastive_Mask_Prediction_ICCV_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Zhao_Self-Supervised_Visual_Representations_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yucheng Zhao, Guangting Wang, Chong Luo, Wenjun Zeng, Zheng-Jun Zha 
 · · Organization(s): University of Science and Technology of China; Microsoft Research Asia 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- Mean Shift for Self-Supervised Learning (**MSF** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Koohpayegani_Mean_Shift_for_Self-Supervised_Learning_ICCV_2021_paper.pdf) [[code]](https://github.com/UMBCvision/MSF) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Koohpayegani_Mean_Shift_for_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash 
 · · Organization(s): University of Maryland, Baltimore County; University of California, Davis 
 · · Description: 
 · · Tags: Positive discovery
 </details>
***
- On Compositions of Transformations in Contrastive Self-Supervised Learning (**GDT** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Patrick_On_Compositions_of_Transformations_in_Contrastive_Self-Supervised_Learning_ICCV_2021_paper.pdf) [[code]](https://github.com/facebookresearch/GDT) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Patrick_On_Compositions_of_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mandela Patrick, Yuki M. Asano, Polina Kuznetsova, Ruth Fong, João F. Henriques, Geoffrey Zweig, Andrea Vedaldi 
 · · Organization(s): Facebook AI Research; Visual Geometry Group, University of Oxford 
 · · Description: 
 · · Tags: 
 </details>
***
- On Feature Decorrelation in Self-Supervised Learning (**Shuffled-DBN** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Hua_On_Feature_Decorrelation_in_Self-Supervised_Learning_ICCV_2021_paper.pdf) [[~~No code~~]]() 
 <details>
 <summary>More Info</summary>
 · · Author(s): Tianyu Hua, Wenxiao Wang, Zihui Xue, Sucheng Ren, Yue Wang, Hang Zhao 
 · · Organization(s): Tsinghua University; Shanghai Qi Zhi Institute; UT Austin; MIT; South China University of Technology 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-supervised Product Quantization for Deep Unsupervised Image Retrieval (**SPQ** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Jang_Self-Supervised_Product_Quantization_for_Deep_Unsupervised_Image_Retrieval_ICCV_2021_paper.pdf) [[code]](https://github.com/youngkyunJang/SPQ) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Young Kyun Jang, Nam Ik Cho 
 · · Organization(s): Department of ECE, INMC, Seoul National University 
 · · Description: 
 · · Tags: 
 </details>
***
- With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations (**NNCLR** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Dwibedi_With_a_Little_Help_From_My_Friends_Nearest-Neighbor_Contrastive_Learning_ICCV_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Dwibedi_With_a_Little_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman 
 · · Organization(s): Google Research; DeepMind 
 · · Description: 
 · · Tags: 
 </details>
***
- Contrasting Contrastive Self-Supervised Representation Learning Pipelines (**ViRB** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Kotar_Contrasting_Contrastive_Self-Supervised_Representation_Learning_Pipelines_ICCV_2021_paper.pdf) [[code]](https://github.com/allenai/virb) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Kotar_Contrasting_Contrastive_Self-Supervised_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Klemen Kotar, Gabriel Ilharco, Ludwig Schmidt, Kiana Ehsani, Roozbeh Mottaghi 
 · · Organization(s): PRIOR @ Allen Institute for AI; University of Washington 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- ISD: Self-Supervised Learning by Iterative Similarity Distillation (**ISD** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Tejankar_ISD_Self-Supervised_Learning_by_Iterative_Similarity_Distillation_ICCV_2021_paper.pdf) [[code]](https://github.com/UMBCvision/ISD) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Tejankar_ISD_Self-Supervised_Learning_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Vipin Pillai, Paolo Favaro, Hamed Pirsiavash 
 · · Organization(s): University of Maryland, Baltimore County; University of Bern; University of California, Davis 
 · · Description: 
 · · Tags: 
 </details>
***
- CDS: Cross-Domain Self-supervised Pre-training (**CDS** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_CDS_Cross-Domain_Self-Supervised_Pre-Training_ICCV_2021_paper.pdf) [[code]](https://github.com/VisionLearningGroup/CDS) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Kim_CDS_Cross-Domain_Self-Supervised_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh, Bryan A. Plummer, Stan Sclaroff, Kate Saenko 
 · · Organization(s): Boston University; POSTECH; MIT-IBM Watson AI Lab 
 · · Description: 
 · · Tags: 
 </details>
***
- Collaborative Unsupervised Visual Representation Learning from Decentralized Data (**FedU** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhuang_Collaborative_Unsupervised_Visual_Representation_Learning_From_Decentralized_Data_ICCV_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Zhuang_Collaborative_Unsupervised_Visual_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai Zhang, Shuai Yi 
 · · Organization(s): S-Lab, Nanyang Technological University; Nanyang Technological University; SenseTime Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Weakly Supervised Contrastive Learning (**WCL** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Zheng_Weakly_Supervised_Contrastive_Learning_ICCV_2021_paper.pdf) [[code]](https://github.com/KyleZheng1997/WCL) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Mingkai Zheng, Fei Wang, Shan You, Chen Qian, Changshui Zhang, Xiaogang Wang, Chang Xu 
 · · Organization(s): SenseTime Research; University of Science and Technology of China; Tsinghua University; The Chinese University of Hong Kong; The University of Sydney 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Representation Learning from Flow Equivariance (**FlowE** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Xiong_Self-Supervised_Representation_Learning_From_Flow_Equivariance_ICCV_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Xiong_Self-Supervised_Representation_Learning_ICCV_2021_supplemental.zip)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yuwen Xiong, Mengye Ren, Wenyuan Zeng, Raquel Urtasun 
 · · Organization(s): Waabi; University of Toronto 
 · · Description: 
 · · Tags:
 </details>
***
- Vi2CLR: Video and Image for Visual Contrastive Learning of Representation (**Vi2CLR** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Diba_Vi2CLR_Video_and_Image_for_Visual_Contrastive_Learning_of_Representation_ICCV_2021_paper.pdf) [[~~No code~~]]() 
 <details>
 <summary>More Info</summary>
 · · Author(s): Ali Diba, Vivek Sharma, Reza Safdari, Dariush Lotfi, Saquib Sarfraz, Rainer Stiefelhagen, Luc Van Gool 
 · · Organization(s): KU Leuven; Sensifai; Karlsruhe Institute of Technology; Daimler TSS; Massachusetts Institute of Technology; Harvard Medical School; ETH Zurich 
 · · Description: 
 · · Tags:
 </details>
***
- Solving Inefficiency of Self-supervised Representation Learning (**truncated triplet** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_Solving_Inefficiency_of_Self-Supervised_Representation_Learning_ICCV_2021_paper.pdf) [[code]](https://github.com/wanggrun/triplet) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Guangrun Wang, Keze Wang, Guangcong Wang, Philip H.S. Torr, Liang Lin 
 · · Organization(s): Sun Yat-sen University; University of Oxford; Nanyang Technological University; DarkMatter AI Research 
 · · Description: 
 · · Tags:
 </details>
***
- Instance Similarity Learning for Unsupervised Feature Representation (**ISL** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_Instance_Similarity_Learning_for_Unsupervised_Feature_Representation_ICCV_2021_paper.pdf) [[code]](https://github.com/ZiweiWangTHU/ISL.git) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Wang_Instance_Similarity_Learning_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Ziwei Wang, Yunsong Wang, Ziyi Wu, Jiwen Lu, Jie Zhou 
 · · Organization(s): Tsinghua University; State Key Lab of Intelligent Technologies and Systems; Beijing National Research Center for Information Science and Technology 
 · · Description: 
 · · Tags:
 </details>
***
- Improving Contrastive Learning by Visualizing Feature Transformation (**** - **ICCV**21 Oral) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhu_Improving_Contrastive_Learning_by_Visualizing_Feature_Transformation_ICCV_2021_paper.pdf) [[code]](https://github.com/DTennant/CL-Visualizing-Feature-Transformation) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Zhu_Improving_Contrastive_Learning_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Rui Zhu, Bingchen Zhao, Jingen Liu, Zhenglong Sun, Chang Wen Chen 
 · · Organization(s): The Chinese University of HongKong, Shenzhen; JD AI Research; Tongji University; The Hong Kong Polytechnic University 
 · · Description: 
 · · Tags:
 </details>
***
- Temporal Knowledge Consistency for Unsupervised Visual Representation Learning (**TKC** - **ICCV**21 Oral) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Feng_Temporal_Knowledge_Consistency_for_Unsupervised_Visual_Representation_Learning_ICCV_2021_paper.pdf) [[~~No code~~]]() [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Feng_Temporal_Knowledge_Consistency_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Weixin Feng, Yuanjiang Wang, Lihua Ma, Ye Yuan, Chi Zhang 
 · · Organization(s): Beijing University of Posts and Telecommunications; Megvii Technology 
 · · Description: 
 · · Tags:
 </details>
***
- MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving (**MultiSiam** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Chen_MultiSiam_Self-Supervised_Multi-Instance_Siamese_Representation_Learning_for_Autonomous_Driving_ICCV_2021_paper.pdf) [[code]](https://github.com/KaiChen1998/MultiSiam) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Chen_MultiSiam_Self-Supervised_Multi-Instance_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Kai Chen, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung 
 · · Organization(s): Hong Kong University of Science and Technology; Huawei Noah’s Ark Lab 
 · · Description: 
 · · Tags: Local representation
 </details>
***
- Region Similarity Representation Learning(**ReSim** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Xiao_Region_Similarity_Representation_Learning_ICCV_2021_paper.pdf) [[code]](https://github.com/Tete-Xiao/ReSim) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Xiao_Region_Similarity_Representation_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Tete Xiao, Colorado J Reed, Xiaolong Wang, Kurt Keutzer, Trevor Darrell 
 · · Organization(s): UC Berkeley; UC San Diego 
 · · Description: 
 · · Tags:
 </details>
***
- Efficient Visual Pretraining With Contrastive Detection(**DetCon** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Henaff_Efficient_Visual_Pretraining_With_Contrastive_Detection_ICCV_2021_paper.pdf) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Henaff_Efficient_Visual_Pretraining_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Olivier J. Hénaff, Skanda Koppula, Jean-Baptiste Alayrac, Aaron van den Oord, Oriol Vinyals, João Carreira 
 · · Organization(s): DeepMind 
 · · Description: 
 · · Tags: Dense
 </details>
***
- An Empirical Study of Training Self-Supervised Vision Transformers(**MoCo-v3** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Chen_An_Empirical_Study_of_Training_Self-Supervised_Vision_Transformers_ICCV_2021_paper.pdf) [[unofficial code]](https://github.com/open-mmlab/mmselfsup) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Chen_An_Empirical_Study_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xinlei Chen, Saining Xie, Kaiming He 
 · · Organization(s): Facebook AI Research (FAIR) 
 · · Description: 
 · · Tags:
 </details>
***
- Emerging Properties in Self-Supervised Vision Transformers(**DINO** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Caron_Emerging_Properties_in_Self-Supervised_Vision_Transformers_ICCV_2021_paper.pdf) [[code]]( https://github.com/facebookresearch/dino) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Caron_Emerging_Properties_in_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, Armand Joulin 
 · · Organization(s): Facebook AI Research; Inria∗; Sorbonne University 
 · · Description: 
 · · Tags:
 </details>
***
- A Broad Study on the Transferability of Visual Representations with Contrastive Learning (**** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Islam_A_Broad_Study_on_the_Transferability_of_Visual_Representations_With_ICCV_2021_paper.pdf) [[code]](https://github.com/asrafulashiq/transfer_broad) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Islam_A_Broad_Study_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Ashraful Islam, Chun-Fu (Richard) Chen, Rameswar Panda, Leonid Karlinsky, Richard Radke, Rogerio Feris 
 · · Organization(s): Rensselaer Polytechnic Institute; MIT-IBM Watson AI Lab; IBM Research 
 · · Description: 
 · · Tags:
 </details>
***
- Concept Generalization in Visual Representation Learning (**CoG** - **ICCV**21) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Sariyildiz_Concept_Generalization_in_Visual_Representation_Learning_ICCV_2021_paper.pdf) [[code]](https://europe.naverlabs.com/cog-benchmark) [[supp]](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Sariyildiz_Concept_Generalization_in_ICCV_2021_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mert Bulent Sariyildiz, Yannis Kalantidis, Diane Larlus, Karteek Alahari 
 · · Organization(s): NAVER LABS Europe; Inria 
 · · Description: 
 · · Tags:
 </details>
***
- Concurrent Discrimination and Alignment for Self-Supervised Feature Learning (**CODIAL** - **ICCVW**21) [[paper]](https://ieeexplore.ieee.org/document/9607472) [[code]](https://github.com/AnjanDutta/codial)
 <details>
 <summary>More Info</summary>
 · · Author(s): Anjan Dutta, Massimiliano Mancini, Zeynep Akata 
 · · Organization(s): University of Exeter; University of T¨ubingen 
 · · Description: 
 · · Tags:
 </details>

## 2020

***
- A critical analysis of self-supervision, or what we can learn from a single image (**** - **ICLR**20 ) [[paper]](https://openreview.net/forum?id=B1esx6EYvr) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Asano YM., Rupprecht C., Vedaldi A. 
 · · Organization(s): VGG, University of Oxford 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- On Mutual Information Maximization for Representation Learning (**** - **ICLR**20 ) [[paper]](https://openreview.net/forum?id=rkxoh24FPH) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic 
 · · Organization(s): Google Research 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- Self-labelling via simultaneous clustering and representation learning (**SeLa** - **ICLR**20 Spotlight) [[paper]](https://openreview.net/forum?id=Hyx-jyBFPr) [[code]](https://github.com/yukimasano/self-label)
 <details>
 <summary>More Info</summary>
 · · Author(s): Asano YM., Rupprecht C., Vedaldi A. 
 · · Organization(s): VGG, University of Oxford 
 · · Description: 
 · · Tags: Clustering
 </details>
***
- Unsupervised Learning of Dense Visual Representations (**VADeR** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/3000311ca56a1cb93397bc676c0b7fff-Abstract.html) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Pedro O. O. Pinheiro, Amjad Almahairi, Ryan Benmalek, Florian Golemo, Aaron C. Courville 
 · · Organization(s): Element AI; Cornell University; Mila, Université de Montréal; CIFAR Fellow 
 · · Description: 
 · · Tags: Dense
 </details>
***
- CompRess: Self-Supervised Learning by Compressing Representations (**CompRess** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/975a1c8b9aee1c48d32e13ec30be7905-Abstract.html) [[code]](https://github.com/UMBCvision/CompRess)
 <details>
 <summary>More Info</summary>
 · · Author(s): Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash 
 · · Organization(s): University of Maryland 
 · · Description: 
 · · Tags: self-supervised distillation
 </details>
***
- Unsupervised Representation Learning by Invariance Propagation (**InvPro** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/23af4b45f1e166141a790d1a3126e77a-Abstract.html) [[code]](https://github.com/WangFeng18/InvariancePropagation)
 <details>
 <summary>More Info</summary>
 · · Author(s): Feng Wang, Huaping Liu, Di Guo, Sun Fuchun 
 · · Organization(s): Tsinghua University 
 · · Description: 
 · · Tags: 
 </details>
***
- Joint Contrastive Learning with Infinite Possibilities (**JCL** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/9523147e5a6707baf674941812ee5c94-Abstract.html) [[code]](https://github.com/caiqi/Joint-Contrastive-Learning)
 <details>
 <summary>More Info</summary>
 · · Author(s): Qi Cai, Yu Wang, Yingwei Pan, Ting Yao, Tao Mei 
 · · Organization(s): University of Science and Technology of China; JD AI Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (**SwAV** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/70feb62b69f16e0238f741fab228fec2-Abstract.html) [[code]](https://github.com/facebookresearch/swav)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin 
 · · Organization(s): Inria; Facebook AI Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Visual Representation Learning from Hierarchical Grouping (**** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/c1502ae5a4d514baec129f72948c266e-Abstract.html) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiao Zhang, Michael Maire 
 · · Organization(s): University of Chicago 
 · · Description: 
 · · Tags: Pixel, Local
 </details>
***
- Parametric Instance Classification for Unsupervised Visual Feature learning (**PIC** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/b427426b8acd2c2e53827970f2c2f526-Abstract.html) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Yue Cao, Zhenda Xie, Bin Liu, Yutong Lin, Zheng Zhang, Han Hu 
 · · Organization(s): Microsoft Research Asia; Tsinghua University; Xi’an Jiaotong University 
 · · Description: 
 · · Tags: 
 </details>
***
- Hard Negative Mixing for Contrastive Learning (**MoCHi** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/f7cade80b7cc92b991cf4d2806d6bd78-Abstract.html) [[code]](https://europe.naverlabs.com/mochi)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel, Diane Larlus 
 · · Organization(s): NAVER LABS Europe 
 · · Description: 
 · · Tags: 
 </details>
***
- What Makes for Good Views for Contrastive Learning? (**InfoMin** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/4c2e5eaae9152079b9e95845750bb9ab-Abstract.html) [[code]](http://github.com/HobbitLong/PyContrast)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan, Cordelia Schmid, Phillip Isola 
 · · Organization(s): MIT; Google Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Debiased Contrastive Learning (**DCL** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/63c3ddcc7b23daa1e42dc41f9a44a873-Abstract.html) [[code]](https://github.com/chingyaoc/DCL)
 <details>
 <summary>More Info</summary>
 · · Author(s): Ching-Yao Chuang, Joshua Robinson, Yen-Chen Lin, Antonio Torralba, Stefanie Jegelka 
 · · Organization(s): Massachusetts Institute of Technology 
 · · Description: 
 · · Tags: False negative
 </details>
***
- Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning (**BYOL** - **NeurIPS**20) [[paper]](https://proceedings.neurips.cc/paper/2020/hash/f3ada80d5c4ee70142b17b8192b2958e-Abstract.html) [[code]](https://github.com/deepmind/deepmind-research/tree/master/byol) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, koray kavukcuoglu, Remi Munos, Michal Valko 
 · · Organization(s): DeepMind; Imperial College 
 · · Description: 
 · · Tags: Siamese architecture
 </details>
***
- MixCo: Mix-up Contrastive Learning for Visual Representation (**MixCo** - **NeurIPSW**20) [[paper]](https://arxiv.org/abs/2010.06300) [[code]](https://github.com/Lee-Gihun/MixCo-Mixup-Contrast) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Sungnyun Kim, Gihun Lee, Sangmin Bae, Se-Young Yun 
 · · Organization(s): KAIST 
 · · Description: 
 · · Tags: 
 </details>

***
- Improved Baselines with Momentum Contrastive Learning (**MoCo v2** - **arXiv**20) [[paper]](https://arxiv.org/pdf/2003.04297) [[code]](https://github.com/facebookresearch/moco) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Xinlei Chen, Haoqi Fan, Ross Girshick, Kaiming He 
 · · Organization(s): Facebook AI Research (FAIR) 
 · · Description: 
 · · Tags: InfoNCE loss, siamese architecture
 </details>

***
- Momentum Contrast for Unsupervised Visual Representation Learning (**MoCo** - **CVPR**20 Oral) [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf) [[code]](https://github.com/facebookresearch/moco) [[supp]](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/He_Momentum_Contrast_for_CVPR_2020_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick 
 · · Organization(s): Facebook AI Research (FAIR) 
 · · Description: Building a dynamic dictionary with a queue and a moving-averaged encoder 
 · · Tags: InfoNCE loss, siamese architecture
 </details>
***
- Online Deep Clustering for Unsupervised Representation Learning (**ODC** - **CVPR**20 Oral) [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zhan_Online_Deep_Clustering_for_Unsupervised_Representation_Learning_CVPR_2020_paper.pdf) [[code]](https://github.com/open-mmlab/mmselfsup) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiaohang Zhan, Jiahao Xie, Ziwei Liu, Yew-Soon Ong, Chen Change Loy 
 · · Organization(s): CUHK - SenseTime Joint Lab, The Chinese University of Hong Kong; Nanyang Technological University; AI3, A*STAR 
 · · Description: 
 · · Tags: 
 </details>
***
- Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics (**LCI** - **CVPR**20) [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Jenni_Steering_Self-Supervised_Feature_Learning_Beyond_Local_Pixel_Statistics_CVPR_2020_paper.pdf) [[code]](https://github.com/sjenni/LCI) [[supp]](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Jenni_Steering_Self-Supervised_Feature_CVPR_2020_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Simon Jenni, Hailin Jin, Paolo Favaro 
 · · Organization(s): University of Bern; Adobe Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Learning Representations by Predicting Bags of Visual Words (**BoWNet** - **CVPR**20) [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Gidaris_Learning_Representations_by_Predicting_Bags_of_Visual_Words_CVPR_2020_paper.pdf) [[code]](https://github.com/valeoai/bownet) [[supp]](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Gidaris_Learning_Representations_by_CVPR_2020_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Perez, Matthieu Cord 
 · · Organization(s): Valeo.ai; University of Crete 
 · · Description: 
 · · Tags: 
 </details>
***
- Probabilistic Structural Latent Representation for Unsupervised Embedding (**PSLR** - **CVPR**20) [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Ye_Probabilistic_Structural_Latent_Representation_for_Unsupervised_Embedding_CVPR_2020_paper.pdf) [[code]](https://github.com/mangye16/PSLR) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Mang Ye, Jianbing Shen 
 · · Organization(s): Inception Institute of Artificial Intelligence 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Learning of Pretext-Invariant Representations (**PIRL** - **CVPR**20) [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Misra_Self-Supervised_Learning_of_Pretext-Invariant_Representations_CVPR_2020_paper.pdf) [[unofficial code]](https://github.com/akwasigroch/Pretext-Invariant-Representations) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Ishan Misra, Laurens van der Maaten 
 · · Organization(s): Facebook AI Research 
 · · Description: 
 · · Tags: 
 </details>
***
- How Useful is Self-Supervised Pretraining for Visual Tasks? (**** - **CVPR**20) [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Newell_How_Useful_Is_Self-Supervised_Pretraining_for_Visual_Tasks_CVPR_2020_paper.pdf) [[code]](github.com/princeton-vl/selfstudy) [[supp]](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Newell_How_Useful_Is_CVPR_2020_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Alejandro Newell, Jia Deng 
 · · Organization(s): Princeton University 
 · · Description: 
 · · Tags: Analysis
 </details>
***
- SCAN: Learning to Classify Images without Labels (**SCAN** - **ECCV**20) [[paper]](https://link.springer.com/chapter/10.1007/978-3-030-58607-2_16) [[code]](https://github.com/wvangansbeke/Unsupervised-Classification) [[arxiv]](https://arxiv.org/abs/2005.12320)
 <details>
 <summary>More Info</summary>
 · · Author(s): Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool 
 · · Organization(s): KU Leuven/ESAT-PSI; ETH Zurich/CVL, TRACE 
 · · Description: 
 · · Tags: 
 </details>
***
- Contrastive Multiview Coding (**CMC** - **ECCV**20) [[paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123560749.pdf) [[code]](http://github.com/HobbitLong/CMC/) [[arxiv]](https://arxiv.org/abs/1906.05849)
 <details>
 <summary>More Info</summary>
 · · Author(s): Yonglong Tian, Dilip Krishnan, Phillip Isola 
 · · Organization(s): MIT CSAIL; Google Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification (**** - **ECCV**20) [[paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123690749.pdf) [[code]](https://github.com/dscig/TwoStageUC) [[~~No arxiv~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): 	Sungwon Han, Sungwon Park, Sungkyu Park, Sundong Kim, Meeyoung Cha 
 · · Organization(s): Korea Advanced Institute of Science and Technology; Data Science Group, Institute for Basic Science 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss (**** - **ECCV**20) [[paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123560137.pdf) [[~~No code~~]]() 
 <details>
 <summary>More Info</summary>
 · · Author(s): Yang Li, Shichao Kan, Zhihai He	 
 · · Organization(s): University of Missouri; Beijing Jiaotong University 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Image Classification for Deep
Representation Learning (**** - **ECCVW**20) [[paper]](https://link.springer.com/chapter/10.1007/978-3-030-66096-3_30) [[~~No code~~]]() [[arxiv]](https://arxiv.org/abs/2006.11480)
 <details>
 <summary>More Info</summary>
 · · Author(s): 	Weijie Chen, Shiliang Pu, Di Xie, Shicai Yang, Yilu Guo, Luojun Lin 
 · · Organization(s): Hikvision Research Institute; School of Electronic and Information Engineering, South China University of Technology 
 · · Description: 
 · · Tags: 
 </details>

## 2019

***
- Learning deep representations by mutual information estimation and maximization (**DIM** - **ICLR**19 Oral) [[paper]](https://openreview.net/forum?id=Bklr3j0cKX) 
 <details>
 <summary>More Info</summary>
 · · Author(s): R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, Yoshua Bengio 
 · · Organization(s): MSR Montreal; MILA; UdeM; IVADO; UNM; U Toronto 
 · · Description: 
 · · Tags: 
 </details>
***
- Learning Representations by Maximizing Mutual Information Across Views (**AMDIM** - **NeurIPS**19) [[paper]](https://proceedings.neurips.cc/paper/2019/hash/ddf354219aac374f1d40b7e760ee5bb7-Abstract.html) [[code]](https://github.com/Philip-Bachman/amdim-public)
 <summary>More Info</summary>
 · · Author(s): Philip Bachman, R Devon Hjelm, William Buchwalte 
 · · Organization(s): Microsoft Research 
 · · Description: 
 · · Tags: 
 </details>
***
- Large Scale Adversarial Representation Learning (**BigBiGAN** - **NeurIPS**19) [[paper]](https://proceedings.neurips.cc/paper/2019/hash/18cdf49ea54eec029238fcc95f76ce41-Abstract.html) 
 <summary>More Info</summary>
 · · Author(s): Jeff Donahue, Karen Simonyan 
 · · Organization(s): DeepMind 
 · · Description: 
 · · Tags: Generative 
 </details>
***
- Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (**ISIF** - **CVPR**19) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Ye_Unsupervised_Embedding_Learning_via_Invariant_and_Spreading_Instance_Feature_CVPR_2019_paper.pdf) [[code]](https://github.com/mangye16/Unsupervised_Embedding_Learning)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mang Ye, Xu Zhang, Pong C. Yuen, Shih-Fu Chang 
 · · Organization(s): Hong Kong Baptist University; Columbia University 
 · · Description: Learning augmentation invariant and instance spread-out features 
 · · Tags: Siamese architecture
 </details>
***
- Self-Supervised Representation Learning by Rotation Feature Decoupling (**FeatureDecoupling** - **CVPR**19) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Feng_Self-Supervised_Representation_Learning_by_Rotation_Feature_Decoupling_CVPR_2019_paper.pdf) [[code]](https://github.com/philiptheother/FeatureDecoupling) [[supp]](https://openaccess.thecvf.com/content_CVPR_2019/supplemental/Feng_Self-Supervised_Representation_Learning_CVPR_2019_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zeyu Feng, Chang Xu, Dacheng Tao 
 · · Organization(s): UBTECH Sydney AI Centre, School of Computer Science; University of Sydney 
 · · Description: 
 · · Tags: 
 </details>
***
- Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning (**** - **CVPR**19) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wei_Iterative_Reorganization_With_Weak_Spatial_Constraints_Solving_Arbitrary_Jigsaw_Puzzles_CVPR_2019_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Chen Wei, Lingxi Xie, Xutong Ren, Yingda Xia, Chi Su, Jiaying Liu, Qi Tian, Alan L. Yuille 
 · · Organization(s): Peking University; The Johns Hopkins University; Kingsoft; Huawei Noah’s Ark Lab 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised GANs via Auxiliary Rotation Loss (**SS-GAN** - **CVPR**19) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_Self-Supervised_GANs_via_Auxiliary_Rotation_Loss_CVPR_2019_paper.pdf) [[code]]( https://github.com/google/compare_gan) [[supp]](https://openaccess.thecvf.com/content_CVPR_2019/supplemental/Chen_Self-Supervised_GANs_via_CVPR_2019_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil Houlsby 
 · · Organization(s): University of California, Los Angeles; Google Brain 
 · · Description: 
 · · Tags: GAN
 </details>
***
- AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data (**AET** - **CVPR**19) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_AET_vs._AED_Unsupervised_Representation_Learning_by_Auto-Encoding_Transformations_Rather_CVPR_2019_paper.pdf) [[code]](https://github.com/maple-research-lab/AET)
 <details>
 <summary>More Info</summary>
 · · Author(s): Liheng Zhang, Guo-Jun Qi, Liqiang Wang, Jiebo Luo 
 · · Organization(s): Huawei Cloud; University of Central Florida; University of Rochester 
 · · Description: 
 · · Tags: 
 </details>
***
- Revisiting Self-Supervised Visual Representation Learning (**** - **CVPR**19) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Kolesnikov_Revisiting_Self-Supervised_Visual_Representation_Learning_CVPR_2019_paper.pdf) [[code]](https://github.com/google/revisiting-self-supervised) [[supp]](https://openaccess.thecvf.com/content_CVPR_2019/supplemental/Kolesnikov_Revisiting_Self-Supervised_Visual_CVPR_2019_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Alexander Kolesnikov, Xiaohua Zhai, Lucas Beyer 
 · · Organization(s): Google Brain 
 · · Description: 
 · · Tags: Revisiting
 </details>
***
- Local Aggregation for Unsupervised Learning of Visual Embeddings (**LA** - **ICCV**19 Oral) [[paper]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhuang_Local_Aggregation_for_Unsupervised_Learning_of_Visual_Embeddings_ICCV_2019_paper.pdf) [[code]](https://github.com/neuroailab/LocalAggregation) [[supp]](https://openaccess.thecvf.com/content_ICCV_2019/supplemental/Zhuang_Local_Aggregation_for_ICCV_2019_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Chengxu Zhuang, Alex Lin Zhai, Daniel Yamins 
 · · Organization(s): Stanford University 
 · · Description: 
 · · Tags: Clustering
 </details>
***
- S4L: Self-Supervised Semi-Supervised Learning (**S4L** - **ICCV**19) [[paper]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhai_S4L_Self-Supervised_Semi-Supervised_Learning_ICCV_2019_paper.pdf) [[code]](https://github.com/google-research/s4l) [[supp]](https://openaccess.thecvf.com/content_ICCV_2019/supplemental/Zhai_S4L_Self-Supervised_Semi-Supervised_ICCV_2019_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiaohua Zhai, Avital Oliver, Alexander Kolesnikov, Lucas Beyer 
 · · Organization(s): Google Research, Brain Team 
 · · Description: 
 · · Tags: 
 </details>
***
- AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations (**AVT** - **ICCV**19) [[paper]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Qi_AVT_Unsupervised_Learning_of_Transformation_Equivariant_Representations_by_Autoencoding_Variational_ICCV_2019_paper.pdf) [[code]](https://github.com/maple-research-lab/AVT-pytorch) [[supp]](https://openaccess.thecvf.com/content_ICCV_2019/supplemental/Qi_AVT_Unsupervised_Learning_ICCV_2019_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Guo-Jun Qi, Liheng Zhang, Chang Wen Chen, Qi Tian 
 · · Organization(s): G1Laboratory for MAchine Perception and LEarning (MAPLE); Huawei Cloud; Huawei Noah’s Ark Lab; The Chinese University of Hong Kong at Shenzhen and Peng Cheng Laboratory 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Representation Learning via Neighborhood-Relational Encoding (**NRE** - **ICCV**19) [[paper]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Sabokrou_Self-Supervised_Representation_Learning_via_Neighborhood-Relational_Encoding_ICCV_2019_paper.pdf) [[~~No code~~]]() 
 <details>
 <summary>More Info</summary>
 · · Author(s): Mohammad Sabokrou, Mohammad Khalooei, Ehsan Adeli 
 · · Organization(s): Institute for Research in Fundamental Sciences; Amirkabir University of Tech.; Stanford University 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Pre-Training of Image Features on Non-Curated Data (**DeeperCluster** - **ICCV**19) [[paper]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Caron_Unsupervised_Pre-Training_of_Image_Features_on_Non-Curated_Data_ICCV_2019_paper.pdf) [[code]](https://github.com/facebookresearch/DeeperCluster) [[supp]](https://openaccess.thecvf.com/content_ICCV_2019/supplemental/Caron_Unsupervised_Pre-Training_of_ICCV_2019_supplemental.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mathilde Caron, Piotr Bojanowski, Julien Mairal, Armand Joulin 
 · · Organization(s): Facebook AI Research; Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK 
 · · Description: 
 · · Tags: Clustering
 </details>
***
- Scaling and Benchmarking Self-Supervised Visual Representation Learning (**** - **ICCV**19) [[paper]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) [[code]](https://github.com/facebookresearch/fair_self_supervision_benchmark) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Priya Goyal, Dhruv Mahajan, Abhinav Gupta, Ishan Misra 
 · · Organization(s): Facebook AI Research 
 · · Description: 
 · · Tags: 
 </details>

## 2018

***
- Unsupervised Representation Learning by Predicting Image Rotations (**RotNet** - **ICLR**18) [[paper]](https://openreview.net/forum?id=S1v4N2l0-) [[code]](https://github.com/gidariss/FeatureLearningRotNet) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Spyros Gidaris, Praveer Singh, Nikos Komodakis 
 · · Organization(s): University Paris-Est; Ecole des Ponts ParisTech 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Feature Learning via Non-Parametric Instance Discrimination ( **InsDis** - **CVPR**18 Spotlight) [[paper]](https://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Unsupervised_Feature_Learning_CVPR_2018_paper.pdf) [[code]](https://github.com/zhirongw/lemniscate.pytorch)
 <details>
 <summary>More Info</summary>
 · · Author(s): Zhirong Wu, Yuanjun Xiong, Stella X. Yu, Dahua Lin 
 · · Organization(s): UC Berkeley/ICSI; Chinese University of Hong Kong; Amazon Rekognition 
 · · Description: 
 · · Tags: Contrastive learning, single branch
 </details>
***
- Improvements to context based self-supervised learning ( **** - **CVPR**18) [[paper]](https://openaccess.thecvf.com/content_cvpr_2018/papers/Mundhenk_Improvements_to_Context_CVPR_2018_paper.pdf) [[code]](https://gdo-datasci.llnl.gov/selfsupervised/) [[supp]](https://openaccess.thecvf.com/content_cvpr_2018/Supplemental/3991-supp.pdf)
 <details>
 <summary>More Info</summary>
 · · Author(s): T. Nathan Mundhenk, Daniel Ho, Barry Y. Chen 
 · · Organization(s): Lawrence Livermore National Laboratory; University of California, Berkeley 
 · · Description: 
 · · Tags: 
 </details>
***
- Self-Supervised Feature Learning by Learning to Spot Artifacts ( **** - **CVPR**18) [[paper]](https://openaccess.thecvf.com/content_cvpr_2018/papers/Jenni_Self-Supervised_Feature_Learning_CVPR_2018_paper.pdf) [[code]](https://github.com/sjenni/LearningToSpotArtifacts)
 <details>
 <summary>More Info</summary>
 · · Author(s): Simon Jenni, Paolo Favaro 
 · · Organization(s): University of Bern 
 · · Description: 
 · · Tags: 
 </details>
***
- Boosting Self-Supervised Learning via Knowledge Transfer ( **** - **CVPR**18) [[paper]](https://openaccess.thecvf.com/content_cvpr_2018/papers/Noroozi_Boosting_Self-Supervised_Learning_CVPR_2018_paper.pdf) [[~~No code~~]]() 
 <details>
 <summary>More Info</summary>
 · · Author(s): Mehdi Noroozi, Ananth Vinjimoor, Paolo Favaro, Hamed Pirsiavash 
 · · Organization(s): University of Bern; University of Maryland, Baltimore County 
 · · Description: 
 · · Tags: Self-supervised Distillation
 </details>
***
- Deep Clustering for Unsupervised Learning of Visual Features ( **DeepCluster** - **ECCV**18) [[paper]](https://www.ecva.net/papers/eccv_2018/papers_ECCV/papers/Mathilde_Caron_Deep_Clustering_for_ECCV_2018_paper.pdf) [[code]](https://github.com/facebookresearch/deepcluster) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Caron, Mathilde and Bojanowski, Piotr and Joulin, Armand and Douze, Matthijs 
 · · Organization(s): Facebook AI Research 
 · · Description: 
 · · Tags: 
 </details>

## 2017

***
- Adversarial Feature Learning (**BiGANs** - **ICLR**18) [[paper]](https://openreview.net/forum?id=BJtNZAFgg) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Jeff Donahue, Philipp Krähenbühl, Trevor Darrell 
 · · Organization(s): University of California, Berkeley; University of Texas, Austin 
 · · Description: 
 · · Tags: 
 </details>
***
- Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction (**Split-Brain Auto** - **CVPR**17 ) [[paper]](https://openaccess.thecvf.com/content_cvpr_2017/papers/Zhang_Split-Brain_Autoencoders_Unsupervised_CVPR_2017_paper.pdf) [[code]](https://github.com/richzhang/splitbrainauto)
 <details>
 <summary>More Info</summary>
 · · Author(s): Richard Zhang, Phillip Isola, Alexei A. Efros 
 · · Organization(s): Berkeley AI Research (BAIR) Laboratory, University of California, Berkeley 
 · · Description: 
 · · Tags: Pretext task
 </details>
***
- Representation Learning by Learning to Count (**** - **ICCV**17 ) [[paper]](https://openaccess.thecvf.com/content_ICCV_2017/papers/Noroozi_Representation_Learning_by_ICCV_2017_paper.pdf) [[unofficial code]](https://github.com/clvrai/Representation-Learning-by-Learning-to-Count)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mehdi Noroozi, Hamed Pirsiavash, Paolo Favaro 
 · · Organization(s): University of Bern; University of Maryland, Baltimore County 
 · · Description: 
 · · Tags: Pretext task
 </details>
***
- Transitive Invariance for Self-supervised Visual Representation Learning (**** - **ICCV**17 ) [[paper]](https://openaccess.thecvf.com/content_ICCV_2017/papers/Wang_Transitive_Invariance_for_ICCV_2017_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiaolong Wang, Kaiming He, Abhinav Gupta 
 · · Organization(s): Carnegie Mellon University; Facebook AI Research 
 · · Description: 
 · · Tags:
 </details>
***
- Multi-task Self-Supervised Visual Learning (**** - **ICCV**17 ) [[paper]](https://openaccess.thecvf.com/content_ICCV_2017/papers/Doersch_Multi-Task_Self-Supervised_Visual_ICCV_2017_paper.pdf) [[code]](https://github.com/deepmind/multiself)
 <details>
 <summary>More Info</summary>
 · · Author(s): Carl Doersch, Andrew Zisserman 
 · · Organization(s): DeepMind; VGG, Department of Engineering Science, University of Oxford 
 · · Description: 
 · · Tags: 
 </details>

## 2016

***
- Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks (**ExemplarCNN** - **TPAMI**16 ) [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7312476) 
 <details>
 <summary>More Info</summary>
 · · Author(s): Alexey Dosovitskiy, Philipp Fischer, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox 
 · · Organization(s): Computer Science Department, University of Freiburg 
 · · Description: 
 · · Tags: Pretext task, Instance Discrimination
 </details>
***
- Context Encoders: Feature Learning by Inpainting (**Inpainting** - **CVPR**16 ) [[paper]](https://openaccess.thecvf.com/content_cvpr_2016/papers/Pathak_Context_Encoders_Feature_CVPR_2016_paper.pdf) [[unofficial code]](https://github.com/BoyuanJiang/context_encoder_pytorch)
 <details>
 <summary>More Info</summary>
 · · Author(s): Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, Alexei A. Efros 
 · · Organization(s): University of California, Berkeley 
 · · Description: 
 · · Tags: Pretext task
 </details>
***
- Unsupervised Learning of Discriminative Attributes and Visual Representations (**** - **CVPR**16 ) [[paper]](https://openaccess.thecvf.com/content_cvpr_2016/papers/Huang_Unsupervised_Learning_of_CVPR_2016_paper.pdf) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Chen Huang, Chen Change Loy, Xiaoou Tang 
 · · Organization(s): The Chinese University of Hong Kong; SenseTime Group Limited; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (**Jigsaw** - **ECCV**16 ) [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-46466-4_5) [[unofficial code]](https://github.com/bbrattoli/JigsawPuzzlePytorch) [[arxiv]](https://arxiv.org/abs/1603.09246)
 <details>
 <summary>More Info</summary>
 · · Author(s): Mehdi Noroozi, Paolo Favaro 
 · · Organization(s): Institute for Informatiks, University of Bern 
 · · Description: 
 · · Tags: Pretext task
 </details>
***
- Unsupervised Visual Representation Learning
by Graph-based Consistent Constraints (**** - **ECCV**16 ) [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-46493-0_41) [[~~No code~~]]()
 <details>
 <summary>More Info</summary>
 · · Author(s): Dong Li, Wei-Chih Hung, Jia-Bin Huang, Shengjin Wang, Narendra Ahuja; Ming-Hsuan Yang 
 · · Organization(s): Tsinghua University; University of California, Merced; University of Illinois, Urbana-Champaign 
 · · Description: 
 · · Tags: 
 </details>
***
- Colorful Image Colorization (**** - **ECCV**16 ) [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-46487-9_40) [[code]](https://github.com/richzhang/colorization)
 <details>
 <summary>More Info</summary>
 · · Author(s): Richard Zhang, Phillip Isola, Alexei A. Efros 
 · · Organization(s): University of California, Berkeley 
 · · Description: 
 · · Tags: 
 </details>

## 2015

***
- Unsupervised Visual Representation Learning by Context Prediction (**Context** - **ICCV**15 ) [[paper]](https://openaccess.thecvf.com/content_iccv_2015/papers/Doersch_Unsupervised_Visual_Representation_ICCV_2015_paper.pdf) [[code]](https://github.com/cdoersch/deepcontext)
 <details>
 <summary>More Info</summary>
 · · Author(s): Carl Doersch, Abhinav Gupta, Alexei A. Efros 
 · · Organization(s): Institute for Informatiks, University of Bern 
 · · Description: 
 · · Tags: Pretext task
 </details>
***
- Learning to See by Moving (**** - **ICCV**15 ) [[paper]](https://openaccess.thecvf.com/content_iccv_2015/papers/Agrawal_Learning_to_See_ICCV_2015_paper.pdf) [[code]](https://github.com/pulkitag/learning-to-see-by-moving)
 <details>
 <summary>More Info</summary>
 · · Author(s): Pulkit Agrawal, Joao Carreira, Jitendra Malik 
 · · Organization(s): UC Berkeley 
 · · Description: 
 · · Tags: 
 </details>
***
- Unsupervised Learning of Visual Representations using Videos (**** - **ICCV**15 ) [[paper]](https://openaccess.thecvf.com/content_iccv_2015/papers/Wang_Unsupervised_Learning_of_ICCV_2015_paper.pdf) [[unofficial code]](https://github.com/coreylynch/unsupervised-triplet-embedding)
 <details>
 <summary>More Info</summary>
 · · Author(s): Xiaolong Wang, Abhinav Gupta 
 · · Organization(s): Robotics Institute, Carnegie Mellon University 
 · · Description: 
 · · Tags: 
 </details>

## 2014

***
- Discriminative Unsupervised Feature Learning with Convolutional Neural Networks (**ExemplarCNN** - **NeurIPS**14 ) [[paper]](https://proceedings.neurips.cc/paper/2014/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf) [[unofficial code]](https://github.com/yihui-he/Exemplar-CNN) [[supp]](https://proceedings.neurips.cc/paper/2014/file/07563a3fe3bbe7e3ba84431ad9d055af-Supplemental.zip)
 <details>
 <summary>More Info</summary>
 · · Author(s): Alexey Dosovitskiy, Jost Tobias Springenberg, Martin A. Riedmiller, Thomas Brox 
 · · Organization(s): Computer Science Department, University of Freiburg 
 · · Description: 
 · · Tags: Pretext task, Instance Discrimination
 </details>

***

UVRL is also closely related to some other research directions, such as **Unsupervised Person (Object or Vehicle) Re-Identification**, **Unsupervised Semantic Segmentation**, **Unsupervised Domain Adaptation**, **Knowledge Distillation**, **Deep Clustering**, **Unsupervised Metric (Embedding) Learning**, **Semi-supervised Learning**, **Novel Categories (Classes) Discovery**, etc.

### **Some Influential Repositories** </details>
***
- awesome-self-supervised-learning (star 5.6k) [[link]](https://github.com/jason718/awesome-self-supervised-learning)

- Awesome-Knowledge-Distillation (star 2.2k) [[link]](https://github.com/FLHonker/Awesome-Knowledge-Distillation)

- DeepClustering (star 2.4k) [[link]](https://github.com/zhoushengisnoob/DeepClustering)

- awesome-metric-learning [[link]](https://github.com/qdrant/awesome-metric-learning)

- Awesome-Unsupervised-Person-Re-identification [[link]](https://github.com/Yimin-Liu/Awesome-Unsupervised-Person-Re-identification)

- Awesome-Novel-Class-Discovery [[link]](https://github.com/JosephKJ/Awesome-Novel-Class-Discovery)

Thanks for the support of Prof. [Yu Zhou](https://people.ucas.ac.cn/~yuzhou).

Unsupervised-Visual-Representation-Learning

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README