ST-SLidR

KO | EN

gitlite — search

#javascript #python #ai #go #machine-learning #deep-learning #macos #nodejs #java #awesome #cli #security #openai #open-source

(★ 12)

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss (CVPR 2023)

ST-SLidR 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# ST-SLidR

`ST-SLidR` is a 2D to 3D distillation framework for autonomous driving scenes. This repository is based off of [`[SLidR]`](https://github.com/valeoai/SLidR).

**Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss**\
*Anas Mahmoud, Jordan Hu, Tianshu Kuai, Ali Harakeh,  Liam Paull,  Steven Waslander*\
**[[Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Mahmoud_Self-Supervised_Image-to-Point_Distillation_via_Semantically_Tolerant_Contrastive_Loss_CVPR_2023_paper.pdf)]**

![Overview of the method](https://raw.githubusercontent.com/TRAILab/ST-SLidR/master/assets/method.png)

## Installation
Please refer to [INSTALL.md](docs/INSTALL.md) for the installation of `ST-SLidR`.

## Results

All results are obtained by pre-training on nuScenes dataset. Each pretraining experiment is conducted 3 times, and the average performance is reported on Linear Probing using 100% of the labelled point cloud data and on finetuning using 1% of the labelled point cloud data.

## Citation
If you use ST-SLidR in your research, please consider citing:
```
@inproceedings{ST-SLidR,
   title = {Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss},
   author = {Anas Mahmoud and Jordan Hu and Tianshu Kuai and Ali Harakeh and  Liam Paull and  Steven Waslander},
   journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   year = {2023}
}
```

## License
`ST-SLidR` is released under the [Apache 2.0 license](./LICENSE).

ST-SLidR

ST-SLidR 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

ST-SLidR

ST-SLidR 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README