deep_learning_object_detection

KO | EN

gitlite — search

#javascript #hacktoberfest #ai #go #android #deep-learning #linux #docker #awesome #cli #vue #pytorch #openai #ios

deep_learning_object_detection

(★ 11,387)

딥러닝을 활용한 객체 탐지(object detection) 관련 논문 모음입니다.

파일 탐색기

최종 버전 다운로드 (.zip)

- deep_learning_object_detection_dataset.PNG
- deep_learning_object_detection_history.PNG
fetch_papers.py
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# deep learning object detection
딥러닝을 이용한 object detection 논문 목록입니다. [이 서베이 논문](https://arxiv.org/pdf/1809.02165v1.pdf)을 참고하고 열심히 검색해서 이 페이지를 작성했습니다.
\*Last updated: 2020/09/22\*
#### Update log
\*2018/9/18\* - 최근 논문들을 모두 업데이트하고 딥러닝을 이용한 object detection의 역사에 관한 다이어그램을 만들었습니다.
\*2018/9/26\* - 논문 코드들을 업데이트했습니다. (공식 및 비공식)
\*2018/october\* - 논문 5편과 성능 표를 업데이트했습니다.
\*2018/november\* - 논문 9편을 업데이트했습니다.
\*2018/december\* - 논문 8편과 성능 표를 업데이트하고 새로운 다이어그램(\*\*2019 version!!\*\*)을 추가했습니다.
\*2019/january\* - 논문 4편을 업데이트하고 자주 사용되는 데이터셋을 추가했습니다.
\*2019/february\* - 논문 3편을 업데이트했습니다.
\*2019/march\* - 그림과 코드 링크를 업데이트했습니다.
\*2019/april\* - 저자 이름을 제거하고 ICLR 2019 및 CVPR 2019 논문들을 업데이트했습니다.
\*2019/may\* - CVPR 2019 논문들을 업데이트했습니다.
\*2019/june\* - CVPR 2019 논문들과 데이터셋 논문을 업데이트했습니다.
\*2019/july\* - BMVC 2019 논문들과 ICCV 2019 논문 일부를 업데이트했습니다.
\*2019/september\* - NeurIPS 2019 논문들과 ICCV 2019 논문들을 업데이트했습니다.
\*2019/november\* - AAAI 2020 논문 일부와 기타 논문들을 업데이트했습니다.
\*2020/january\* - ICLR 2020 논문들과 기타 논문들을 업데이트했습니다.
\*2020/may\* - CVPR 2020 논문들과 기타 논문들을 업데이트했습니다.
\*2020/june\* - arxiv 논문들을 업데이트했습니다.
\*2020/august\* - 논문 링크를 업데이트했습니다.
##
## Table of Contents
- [Paper list from 2014 to now(2019)](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#paper-list-from-2014-to-now2019)
- [Performance table](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#performance-table)
- Papers
- [2014](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#2014)
- [2015](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#2015)
- [2016](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#2016)
- [2017](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#2017)
- [2018](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#2018)
- [2019](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#2019)
- [2020](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#2020)
- [Dataset Papers](https://github.com/hoya012/deep\_learning\_object\_detection/blob/master/README.md#dataset-papers)
##
## Paper list from 2014 to now(2019)
빨간색 글씨로 강조된 부분은 제가 생각하기에 "필독"해야 하는 논문들을 의미합니다.
하지만 이는 \*\*저의 개인적인 의견\*\*이며 다른 논문들도 중요하므로 시간이 있다면 읽어보시는 것을 추천합니다.

![](/assets/deep_learning_object_detection_history.PNG)

##
## 성능 표
FPS(속도) 지수는 하드웨어 사양(예: CPU, GPU, RAM 등)과 관련이 있으므로 동등한 비교가 어렵습니다. 해결책은 동등한 사양의 하드웨어에서 모든 모델의 성능을 측정하는 것이지만, 이는 매우 어렵고 시간이 오래 걸립니다.
| Detector | VOC07 (mAP@IoU=0.5) | VOC12 (mAP@IoU=0.5) | COCO (mAP@IoU=0.5:0.95) | Published In |
|:------------:|:-------------------:|:-------------------:|:----------:|:------------:|
| R-CNN | 58.5 | - | - | CVPR'14 |
| SPP-Net | 59.2 | - | - | ECCV'14 |
| MR-CNN | 78.2 (07+12) | 73.9 (07+12) | - | ICCV'15 |
| Fast R-CNN | 70.0 (07+12) | 68.4 (07++12) | 19.7 | ICCV'15 |
| Faster R-CNN | 73.2 (07+12) | 70.4 (07++12) | 21.9 | NIPS'15 |
| YOLO v1 | 66.4 (07+12) | 57.9 (07++12) | - | CVPR'16 |
| G-CNN | 66.8 | 66.4 (07+12) | - | CVPR'16 |
| AZNet | 70.4 | - | 22.3 | CVPR'16 |
| ION | 80.1 | 77.9 | 33.1 | CVPR'16 |
| HyperNet | 76.3 (07+12) | 71.4 (07++12) | - | CVPR'16 |
| OHEM | 78.9 (07+12) | 76.3 (07++12) | 22.4 | CVPR'16 |
| MPN | - | - | 33.2 | BMVC'16 |
| SSD | 76.8 (07+12) | 74.9 (07++12) | 31.2 | ECCV'16 |
| GBDNet | 77.2 (07+12) | - | 27.0 | ECCV'16 |
| CPF | 76.4 (07+12) | 72.6 (07++12) | - | ECCV'16 |
| R-FCN | 79.5 (07+12) | 77.6 (07++12) | 29.9 | NIPS'16 |
| DeepID-Net | 69.0 | - | - | PAMI'16 |
| NoC | 71.6 (07+12) | 68.8 (07+12) | 27.2 | TPAMI'16 |
| DSSD | 81.5 (07+12) | 80.0 (07++12) | 33.2 | arXiv'17 |
| TDM | - | - | 37.3 | CVPR'17 |
| FPN | - | - | 36.2 | CVPR'17 |
| YOLO v2 | 78.6 (07+12) | 73.4 (07++12) | - | CVPR'17 |
| RON | 77.6 (07+12) | 75.4 (07++12) | 27.4 | CVPR'17 |
| DeNet | 77.1 (07+12) | 73.9 (07++12) | 33.8 | ICCV'17 |
| CoupleNet | 82.7 (07+12) | 80.4 (07++12) | 34.4 | ICCV'17 |
| RetinaNet | - | - | 39.1 | ICCV'17 |
| DSOD | 77.7 (07+12) | 76.3 (07++12) | - | ICCV'17 |
| SMN | 70.0 | - | - | ICCV'17 |
|Light-Head R-CNN| - | - | 41.5 | arXiv'17 |
| YOLO v3 | - | - | 33.0 | arXiv'18 |
| SIN | 76.0 (07+12) | 73.1 (07++12) | 23.2 | CVPR'18 |
| STDN | 80.9 (07+12) | - | - | CVPR'18 |
| RefineDet | 83.8 (07+12) | 83.5 (07++12) | 41.8 | CVPR'18 |
| SNIP | - | - | 45.7 | CVPR'18 |
|Relation-Network| - | - | 32.5 | CVPR'18 |
| Cascade R-CNN| - | - | 42.8 | CVPR'18 |
| MLKP | 80.6 (07+12) | 77.2 (07++12) | 28.6 | CVPR'18 |
| Fitness-NMS | - | - | 41.8 | CVPR'18 |
| RFBNet | 82.2 (07+12) | - | - | ECCV'18 |
| CornerNet | - | - | 42.1 | ECCV'18 |
| PFPNet | 84.1 (07+12) | 83.7 (07++12) | 39.4 | ECCV'18 |
| Pelee | 70.9 (07+12) | - | - | NIPS'18 |
| HKRM | 78.8 (07+12) | - | 37.8 | NIPS'18 |
| M2Det | - | - | 44.2 | AAAI'19 |
| R-DAD | 81.2 (07++12) | 82.0 (07++12) | 43.1 | AAAI'19 |
| ScratchDet | 84.1 (07++12) | 83.6 (07++12) | 39.1 | CVPR'19 |
| Libra R-CNN | - | - | 43.0 | CVPR'19 |
| Reasoning-RCNN | 82.5 (07++12) | - | 43.2 | CVPR'19 |
| FSAF | - | - | 44.6 | CVPR'19 |
| AmoebaNet + NAS-FPN | - | - | 47.0 | CVPR'19 |
| Cascade-RetinaNet | - | - | 41.1 | CVPR'19 |
| HTC | - | - | 47.2 | CVPR'19 |
| TridentNet | - | - | 48.4 | ICCV'19 |
| DAFS | \*\*85.3 (07+12)\*\* | 83.1 (07++12) | 40.5 | ICCV'19 |
| Auto-FPN | 81.8 (07++12) | - | 40.5 | ICCV'19 |
| FCOS | - | - | 44.7 | ICCV'19 |
| FreeAnchor | - | - | 44.8 | NeurIPS'19 |
| DetNAS | 81.5 (07++12) | - | 42.0 | NeurIPS'19 |
| NATS | - | - | 42.0 | NeurIPS'19 |
| AmoebaNet + NAS-FPN + AA | - | - | 50.7 | arXiv'19 |
| SpineNet | - | - | 52.1 | arXiv'19 |
| CBNet | - | - | 53.3 | AAAI'20 |
| EfficientDet | - | - | 52.6 | CVPR'20 |
| DetectoRS | - | - | \*\*54.7\*\* | arXiv'20 |
##
## 2014
- \*\*[R-CNN]\*\* Rich feature hierarchies for accurate object detection and semantic segmentation | \*\*[CVPR' 14]\*\* |[`[pdf]`](https://arxiv.org/pdf/1311.2524.pdf) [`[official code - caffe]`](https://github.com/rbgirshick/rcnn)
- \*\*[OverFeat]\*\* OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks | \*\*[ICLR' 14]\*\* |[`[pdf]`](https://arxiv.org/pdf/1312.6229.pdf) [`[official code - torch]`](https://github.com/sermanet/OverFeat)
- \*\*[Multi

Box]\*\* Scalable Object Detection using Deep Neural Networks | \*\*[CVPR' 14]\*\* |[`[pdf]`](https://www.cv-foundation.org/openaccess/content\_cvpr\_2014/papers/Erhan\_Scalable\_Object\_Detection\_2014\_CVPR\_paper.pdf)
- \*\*[SPP-Net]\*\* Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition | \*\*[ECCV' 14]\*\* |[`[pdf]`](https://arxiv.org/pdf/1406.4729.pdf) [`[official code - caffe]`](https://github.com/ShaoqingRen/SPP\_net) [`[unofficial code - keras]`](https://github.com/yhenon/keras-spp) [`[unofficial code - tensorflow]`](https://github.com/peace195/sppnet)
## 2015
- Bayesian Optimization과 Structured Prediction을 통한 심층 합성곱 신경망 기반 객체 검출 성능 개선 | \*\*[CVPR' 15]\*\* |[`[pdf]`](https://arxiv.org/pdf/1504.03293.pdf) [`[official code - matlab]`](https://github.com/YutingZhang/fgs-obj)
- \*\*[MR-CNN]\*\* 다중 영역 및 시의적/의미적 분할 인식 CNN 모델을 이용한 객체 검출 | \*\*[ICCV' 15]\*\* |[`[pdf]`](https://www.cv-foundation.org/openaccess/content\_iccv\_2015/papers/Gidaris\_Object\_Detection\_via\_ICCV\_2015\_paper.pdf) [`[official code - caffe]`](https://github.com/gidariss/mrcnn-object-detection)
- \*\*[DeepBox]\*\* DeepBox: 합성곱 신경망을 이용한 객체성 학습 | \*\*[ICCV' 15]\*\* |[`[pdf]`](https://arxiv.org/pdf/1505.02146.pdf) [`[official code - caffe]`](https://github.com/weichengkuo/DeepBox)
- \*\*[AttentionNet]\*\* AttentionNet: 정확한 객체 검출을 위한 약한 방향성 집계 | \*\*[ICCV' 15]\*\* |[`[pdf]`](https://arxiv.org/pdf/1506.07704.pdf)
- \*\*[Fast R-CNN]\*\* Fast R-CNN | \*\*[ICCV' 15]\*\* |[`[pdf]`](https://arxiv.org/pdf/1504.08083.pdf) [`[official code - caffe]`](https://github.com/rbgirshick/fast-rcnn)
- \*\*[DeepProposal]\*\* DeepProposal: 심층 합성곱 레이어의 캐스케이딩을 통한 객체 탐색 | \*\*[ICCV' 15]\*\* |[`[pdf]`](https://arxiv.org/pdf/1510.04445.pdf) [`[official code - matconvnet]`](https://github.com/aghodrati/deepproposal)
- \*\*[Faster R-CNN, RPN]\*\* Faster R-CNN: 영역 제안 네트워크를 이용한 실시간 객체 검출을 향하여 | \*\*[NIPS' 15]\*\* |[`[pdf]`](https://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.pdf) [`[official code - caffe]`](https://github.com/rbgirshick/py-faster-rcnn) [`[unofficial code - tensorflow]`](https://github.com/endernewton/tf-faster-rcnn) [`[unofficial code - pytorch]`](https://github.com/jwyang/faster-rcnn.pytorch)
## 2016
- \*\*[YOLO v1]\*\* You Only Look Once: 통합된 실시간 객체 검출 | \*\*[CVPR' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1506.02640.pdf) [`[official code - c]`](https://pjreddie.com/darknet/yolo/)
- \*\*[G-CNN]\*\* G-CNN: 반복적 그리드 기반 객체 검출기 | \*\*[CVPR' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1512.07729.pdf)
- \*\*[AZNet]\*\* 인접성 및 줌 예측을 사용한 적응형 객체 검출 | \*\*[CVPR' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1512.07711.pdf)
- \*\*[ION]\*\* Inside-Outside Net: 스킵 풀링과 순환 신경망을 이용한 문맥 속 객체 검출 | \*\*[CVPR' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1512.04143.pdf)
- \*\*[HyperNet]\*\* HyperNet: 정확한 영역 제안 생성 및 결합 객체 검출을 향하여 | \*\*[CVPR' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1604.00600.pdf)
- \*\*[OHEM]\*\* 온라인 하드 예제 마이닝을 이용한 영역 기반 객체 검출기 학습 | \*\*[CVPR' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1604.03540.pdf) [`[official code - caffe]`](https://github.com/abhi2610/ohem)
- \*\*[CRAPF]\*\* 이미지에서 CRAFT 객체 검출 | \*\*[CVPR' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1604.03239.pdf) [`[official code - caffe]`](https://github.com/byangderek/CRAFT)
- \*\*[MPN]\*\* 객체 검출을 위한 멀티패스 네트워크 | \*\*[BMVC' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1604.02135.pdf) [`[official code - torch]`](https://github.com/facebookresearch/multipathnet)
- \*\*[SSD]\*\* SSD: Single Shot MultiBox Detector | \*\*[ECCV' 16]

\*\* |[`[pdf]`](https://arxiv.org/pdf/1512.02325.pdf) [`[official code - caffe]`](https://github.com/weiliu89/caffe/tree/ssd) [`[unofficial code - tensorflow]`](https://github.com/balancap/SSD-Tensorflow) [`[unofficial code - pytorch]`](https://github.com/amdegroot/ssd.pytorch)
- \*\*[GBDNet]\*\* 객체 검출을 위한 GBD-Net 제작 | \*\*[ECCV' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1610.02579.pdf) [`[official code - caffe]`](https://github.com/craftGBD/craftGBD)
- \*\*[CPF]\*\* Faster R-CNN을 위한 문맥적 프라이밍 및 피드백 | \*\*[ECCV' 16]\*\* |[`[pdf]`](https://pdfs.semanticscholar.org/40e7/4473cb82231559cbaeaa44989e9bbfe7ec3f.pdf)
- \*\*[MS-CNN]\*\* 빠른 객체 검출을 위한 통합 다중 스케일 심층 합성곱 신경망 | \*\*[ECCV' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1607.07155.pdf) [`[official code - caffe]`](https://github.com/zhaoweicai/mscnn)
- \*\*[R-FCN]\*\* R-FCN: 영역 기반 완전 합성곱 신경망을 이용한 객체 검출 | \*\*[NIPS' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1605.06409.pdf) [`[official code - caffe]`](https://github.com/daijifeng001/R-FCN) [`[unofficial code - caffe]`](https://github.com/YuwenXiong/py-R-FCN)
- \*\*[PVANET]\*\* PVANET: 실시간 객체 검출을 위한 깊지만 경량화된 신경망 | \*\*[NIPSW' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1608.08021.pdf) [`[official code - caffe]`](https://github.com/sanghoon/pva-faster-rcnn)
- \*\*[DeepID-Net]\*\* DeepID-Net: 객체 검출을 위한 변형 가능한 심층 합성곱 신경망 | \*\*[PAMI' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1412.5661.pdf)
- \*\*[NoC]\*\* 합성곱 특징 맵에서의 객체 검출 신경망 | \*\*[TPAMI' 16]\*\* |[`[pdf]`](https://arxiv.org/pdf/1504.06066.pdf)
## 2017
- \*\*[DSSD]\*\* DSSD : 역합성곱 단일 샷 검출기 | \*\*[arXiv' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1701.06659.pdf) [`[official code - caffe]`](https://github.com/chengyangfu/caffe/tree/dssd)
- \*\*[TDM]\*\* 스킵 연결을 넘어서: 객체 검출을 위한 하향식 조절 | \*\*[CVPR' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1612.06851.pdf)
- \*\*[FPN]\*\* 객체 검출을 위한 피라미드 네트워크 특징 | \*\*[CVPR' 17]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2017/papers/Lin\_Feature\_Pyramid\_Networks\_CVPR\_2017\_paper.pdf) [`[unofficial code - caffe]`](https://github.com/unsky/FPN)
- \*\*[YOLO v2]\*\* YOLO9000: 더 좋고, 더 빠르고, 더 강력하게 | \*\*[CVPR' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1612.08242.pdf) [`[official code - c]`](https://pjreddie.com/darknet/yolo/) [`[unofficial code - caffe]`](https://github.com/quhezheng/caffe\_yolo\_v2) [`[unofficial code - tensorflow]`](https://github.com/nilboy/tensorflow-yolo) [`[unofficial code - tensorflow]`](https://github.com/sualab/object-detection-yolov2) [`[unofficial code - pytorch]`](https://github.com/longcw/yolo2-pytorch)
- \*\*[RON]\*\* RON: 객체성 사전 네트워크를 이용한 역방향 연결 객체 검출 | \*\*[CVPR' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1707.01691.pdf) [`[official code - caffe]`](https://github.com/taokong/RON) [`[unofficial code - tensorflow]`](https://github.com/HiKapok/RON\_Tensorflow)
- \*\*[RSA]\*\* CNN에서의 객체 검출을 위한 순환 스케일 근사 | | \*\*[ICCV' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1707.09531.pdf) [`[official code - caffe]`](https://github.com/sciencefans/RSA-for-object-detection)
- \*\*[DCN]\*\* 변형 가능한 합성곱 신경망 | \*\*[ICCV' 17]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2017/papers/Dai\_Deformable\_Convolutional\_Networks\_ICCV\_2017\_paper.pdf) [`[official code - mxnet]`](https://github.com/msracver/Deformable-ConvNets) [`[unofficial code - tensorflow]`](https://github.com/Zardinality/TF\_Deformable\_Net) [`[unofficial code - pytorch]`](https://github.com/oeway/pytorch-deform-conv)
- \*\*[DeNet]\*\* DeNet: 유향 희소 샘플링을 이용한 확장 가능한 실시간 객체 검출 | \*\*[ICCV' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1703.10295.pdf)

f) [`[official code - theano]`](https://github.com/lachlants/denet)
- \*\*[CoupleNet]\*\* CoupleNet: 객체 검출을 위한 전역 구조와 지역 부품의 결합 | \*\*[ICCV' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1708.02863.pdf) [`[official code - caffe]`](https://github.com/tshizys/CoupleNet)
- \*\*[RetinaNet]\*\* 조밀한 객체 검출을 위한 Focal Loss | \*\*[ICCV' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1708.02002.pdf) [`[official code - keras]`](https://github.com/fizyr/keras-retinanet) [`[unofficial code - pytorch]`](https://github.com/kuangliu/pytorch-retinanet) [`[unofficial code - mxnet]`](https://github.com/unsky/RetinaNet) [`[unofficial code - tensorflow]`](https://github.com/tensorflow/tpu/tree/master/models/official/retinanet)
- \*\*[Mask R-CNN]\*\* Mask R-CNN | \*\*[ICCV' 17]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2017/papers/He\_Mask\_R-CNN\_ICCV\_2017\_paper.pdf) [`[official code - caffe2]`](https://github.com/facebookresearch/Detectron) [`[unofficial code - tensorflow]`](https://github.com/matterport/Mask\_RCNN) [`[unofficial code - tensorflow]`](https://github.com/CharlesShang/FastMaskRCNN) [`[unofficial code - pytorch]`](https://github.com/multimodallearning/pytorch-mask-rcnn)
- \*\*[DSOD]\*\* DSOD: 처음부터 심층 지도 객체 검출기 학습하기 | \*\*[ICCV' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1708.01241.pdf) [`[official code - caffe]`](https://github.com/szq0214/DSOD) [`[unofficial code - pytorch]`](https://github.com/uoip/SSD-variants)
- \*\*[SMN]\*\* 객체 검출에서 컨텍스트 추론을 위한 공간 메모리 | \*\*[ICCV' 17]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2017/papers/Chen\_Spatial\_Memory\_for\_ICCV\_2017\_paper.pdf)
- \*\*[Light-Head R-CNN]\*\* Light-Head R-CNN: 투 스테이지 객체 검출기의 옹호 | \*\*[arXiv' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1711.07264.pdf) [`[official code - tensorflow]`](https://github.com/zengarden/light\_head\_rcnn)
- \*\*[Soft-NMS]\*\* 단 한 줄의 코드로 객체 검출 성능 향상하기 | \*\*[ICCV' 17]\*\* |[`[pdf]`](https://arxiv.org/pdf/1704.04503.pdf) [`[official code - caffe]`](https://github.com/bharatsingh430/soft-nms)
## 2018
- \*\*[YOLO v3]\*\* YOLOv3: 점진적 개선 | \*\*[arXiv' 18]\*\* |[`[pdf]`](https://pjreddie.com/media/files/papers/YOLOv3.pdf) [`[official code - c]`](https://pjreddie.com/darknet/yolo/) [`[unofficial code - pytorch]`](https://github.com/ayooshkathuria/pytorch-yolo-v3) [`[unofficial code - pytorch]`](https://github.com/eriklindernoren/PyTorch-YOLOv3) [`[unofficial code - keras]`](https://github.com/qqwweee/keras-yolo3) [`[unofficial code - tensorflow]`](https://github.com/mystic123/tensorflow-yolo-v3)
- \*\*[ZIP]\*\* 객체 제안을 위한 재귀 학습 기반 줌 아웃-앤-인 네트워크 | \*\*[IJCV' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1702.05711.pdf) [`[official code - caffe]`](https://github.com/hli2020/zoom\_network)
- \*\*[SIN]\*\* 구조 추론넷: 장면 수준 컨텍스트와 인스턴스 수준 관계를 이용한 객체 검출 | \*\*[CVPR' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2018/papers/Liu\_Structure\_Inference\_Net\_CVPR\_2018\_paper.pdf) [`[official code - tensorflow]`](https://github.com/choasup/SIN)
- \*\*[STDN]\*\* 스케일 전송 가능 객체 검출 | \*\*[CVPR' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2018/papers/Zhou\_Scale-Transferrable\_Object\_Detection\_CVPR\_2018\_paper.pdf)
- \*\*[RefineDet]\*\* 객체 검출을 위한 단일 샷 정제 신경망 | \*\*[CVPR' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2018/papers/Zhang\_Single-Shot\_Refinement\_Neural\_CVPR\_2018\_paper.pdf) [`[official code - caffe]`](https://github.com/sfzhang15/RefineDet) [`[unofficial code - chainer]`](https://github.com/fukatani/RefineDet\_chainer) [`[unofficial code - pytorch]`](https://github.com/lzx1413/PytorchSSD)
- \*\*[MegDet]\*\* MegDet: 대규모 미니배치 객체 검출기 | \*\*[CVPR' 18]\*\*

\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2018/papers/Peng\_MegDet\_A\_Large\_CVPR\_2018\_paper.pdf)
- \*\*[DA Faster R-CNN]\*\* Domain Adaptive Faster R-CNN for Object Detection in the Wild | \*\*[CVPR' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2018/papers/Chen\_Domain\_Adaptive\_Faster\_CVPR\_2018\_paper.pdf) [`[official code - caffe]`](https://github.com/yuhuayc/da-faster-rcnn)
- \*\*[SNIP]\*\* An Analysis of Scale Invariance in Object Detection – SNIP | \*\*[CVPR' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1711.08189.pdf)
- \*\*[Relation-Network]\*\* Relation Networks for Object Detection | \*\*[CVPR' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1711.11575.pdf) [`[official code - mxnet]`](https://github.com/msracver/Relation-Networks-for-Object-Detection)
- \*\*[Cascade R-CNN]\*\* Cascade R-CNN: Delving into High Quality Object Detection | \*\*[CVPR' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2018/papers/Cai\_Cascade\_R-CNN\_Delving\_CVPR\_2018\_paper.pdf) [`[official code - caffe]`](https://github.com/zhaoweicai/cascade-rcnn)
- Generative Adversarial Network를 이용한 야외 환경에서의 작은 얼굴 탐지 | \*\*[CVPR' 18]\*\* |[`[pdf]`](https://ivul.kaust.edu.sa/Documents/Publications/2018/Finding%20Tiny%20Faces%20in%20the%20Wild%20with%20Generative%20Adversarial%20Network.pdf)
- \*\*[MLKP]\*\* Multi-scale Location-aware Kernel Representation for Object Detection | \*\*[CVPR' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1804.00428.pdf) [`[official code - caffe]`](https://github.com/Hwang64/MLKP)
- 점진적 도메인 적응을 통한 크로스 도메인 약지도 객체 탐지 | \*\*[CVPR' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1803.11365.pdf) [`[official code - chainer]`](https://github.com/naoto0804/cross-domain-detection)
- \*\*[Fitness NMS]\*\* Improving Object Localization with Fitness NMS and Bounded IoU Loss | \*\*[CVPR' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_cvpr\_2018/CameraReady/0794.pdf)
- \*\*[STDnet]\*\* STDnet: A ConvNet for Small Target Detection | \*\*[BMVC' 18]\*\* |[`[pdf]`](http://bmvc2018.org/contents/papers/0897.pdf)
- \*\*[RFBNet]\*\* Receptive Field Block Net for Accurate and Fast Object Detection | \*\*[ECCV' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1711.07767.pdf) [`[official code - pytorch]`](https://github.com/ruinmessi/RFBNet)
- 웹 지식 전파를 활용한 제로 어노테이션 객체 탐지 | \*\*[ECCV' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ECCV\_2018/papers/Qingyi\_Tao\_Zero-Annotation\_Object\_Detection\_ECCV\_2018\_paper.pdf)
- \*\*[CornerNet]\*\* CornerNet: Detecting Objects as Paired Keypoints | \*\*[ECCV' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1808.01244.pdf) [`[official code - pytorch]`](https://github.com/princeton-vl/CornerNet)
- \*\*[PFPNet]\*\* Parallel Feature Pyramid Network for Object Detection | \*\*[ECCV' 18]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ECCV\_2018/papers/Seung-Wook\_Kim\_Parallel\_Feature\_Pyramid\_ECCV\_2018\_paper.pdf)
- \*\*[Softer-NMS]\*\* Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection | \*\*[arXiv' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1809.08545.pdf)
- \*\*[ShapeShifter]\*\* ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector | \*\*[ECML-PKDD' 18]\*\* |[`[pdf]`](https://arxiv.org/pdf/1804.05810.pdf) [`[official code - tensorflow]`](https://github.com/shangtse/robust-physical-attack)
- \*\*[Pelee]\*\* Pelee: A Real-Time Object Detection System on Mobile Devices | \*\*[NIPS' 18]\*\* |[`[pdf]`](http://papers.nips.cc/paper/7466-pelee-a-real-time-object-detection-system-on-mobile-devices.pdf) [`[official code - caffe]`](https://github.com/Robert-JunWang/Pelee)
- \*\*[HKRM]\*\* Hybrid Knowledge Routed Modules for Large-scale Object Detection | \*\*[NIPS' 18]\*\* |[`[pdf]`](http://papers.nips.cc/paper/7428-hybrid-knowledge-routed-modules-for-large-scale-object-detection.pdf)
- \*\*[MetaAnchor]\*\* MetaAnchor: Learn

ing to Detect Objects with Customized Anchors | \*\*[NIPS' 18]\*\* |[`[pdf]`](http://papers.nips.cc/paper/7315-metaanchor-learning-to-detect-objects-with-customized-anchors.pdf)
- \*\*[SNIPER]\*\* SNIPER: 효율적인 다중 스케일 학습 (Efficient Multi-Scale Training) | \*\*[NIPS' 18]\*\* |[`[pdf]`](http://papers.nips.cc/paper/8143-sniper-efficient-multi-scale-training.pdf)
## 2019
- \*\*[M2Det]\*\* M2Det: 멀티 레벨 피처 피라미드 네트워크 기반 단일 샷 객체 검출기 (A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network) | \*\*[AAAI' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1811.04533.pdf) [`[official code - pytorch]`](https://github.com/qijiezhao/M2Det)
- \*\*[R-DAD]\*\* 영역 분할 및 조립 기반 객체 검출 (Object Detection based on Region Decomposition and Assembly) | \*\*[AAAI' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1901.08225v1.pdf)
- \*\*[CAMOU]\*\* CAMOU: 야외에서 적대적으로 검출기를 공격하기 위한 물리적 차량 위장 학습 (Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild) | \*\*[ICLR' 19]\*\* |[`[pdf]`](https://openreview.net/pdf?id=SJgEl3A5tm)
- 객체 검출을 위한 피처 인터트와이너 (Feature Intertwiner for Object Detection) | \*\*[ICLR' 19]\*\* |[`[pdf]`](https://openreview.net/pdf?id=SyxZJn05YX)
- \*\*[GIoU]\*\* 일반화된 최소 교집합 합집합 비율: 바운딩 박스 회귀를 위한 지표 및 손실 함수 (Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1902.09630.pdf)
- 자기 학습을 이용한 새로운 도메인용 객체 검출기 자동 적응 (Automatic adaptation of object detectors to new domains using self-training) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.07305.pdf)
- \*\*[Libra R-CNN]\*\* Libra R-CNN: 객체 검출을 위한 균형 잡힌 학습 (Balanced Learning for Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.02701.pdf)
- \*\*[FSAF]\*\* 단일 샷 객체 검출을 위한 피처 선택적 앵커 프리 모듈 (Feature Selective Anchor-Free Module for Single-Shot Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1903.00621.pdf)
- \*\*[ExtremeNet]\*\* 익스트림 및 센터 포인트 그룹화를 통한 상향식 객체 검출 (Bottom-up Object Detection by Grouping Extreme and Center Points) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1901.08043.pdf) | [`[official code - pytorch]`](https://github.com/xingyizhou/ExtremeNet)
- \*\*[C-MIL]\*\* C-MIL: 약지도 객체 검출을 위한 연속 다중 인스턴스 학습 (Continuation Multiple Instance Learning for Weakly Supervised Object Detection)
| \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.05647.pdf) | [`[official code - torch]`](https://github.com/AnonymousIDs/C-MIL)
- \*\*[ScratchDet]\*\* ScratchDet: 처음부터 단일 샷 객체 검출기 학습하기 (Training Single-Shot Object Detectors from Scratch) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1810.08425.pdf)
- 정확한 객체 검출을 위한 불확실성을 포함한 바운딩 박스 회귀 (Bounding Box Regression with Uncertainty for Accurate Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1809.08545.pdf) | [`[official code - caffe2]`](https://github.com/yihui-he/KL-Loss)
- 행동 기반 약지도 객체 검출 (Activity Driven Weakly Supervised Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.01665.pdf)
- AP-Loss를 이용한 정확한 원스테이지 객체 검출을 향하여 (Towards Accurate One-Stage Object Detection with AP-Loss) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.06373.pdf)
- 적응형 객체 검출을 위한 강-약 분포 정렬 (Strong-Weak Distribution Alignment for Adaptive Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1812.04798.pdf) | [`[official code - pytorch]`](https://github.com/VisionLearningGroup/DA\_Detection)
- \*\*[NAS-FPN]\*\* NAS-FPN: 객체 검출을 위한 확장 가능한 피처 피라미드 아키텍처 학습 (Learning Scalable Feature Pyramid Architecture for Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.07392.pdf)
- \*\*[Adaptive NMS]\*\* Adaptive NMS: 군중 속 보행자 검출 정교화 (Refining Pedestrian Detection in a Crowd) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.03629.pdf)
- 점을 넣고 상자를 얻다: 군중 속 사람 수 세기를 넘어서 (Point in, Box out: Beyond Counting Persons in Crowds) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.01333.pdf)
- 바운딩 박스 없이 객체 위치 파악하기 (Locating Objects Without Bounding Boxes) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1806.07564.pdf)
- 드물게 주석이 달린 객체로부터의 대규모 객체 검출을 위한 샘플링 기법 (Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1811.10862.pdf)
- 도메인 어텐션을 통한 범용 객체 검출을 향하여 (Towards Universal Object Detection by Domain Attention) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.04402.pdf)
- 객체 검출을 위한 컨텍스트 유용성의 한계 탐색 (Exploring the Bounds of the Utility of Context for Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1711.05471.pdf)
- 어떤 객체를 사용해야 할까? - 태스크 기반 Ob

ject Detection | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.03000.pdf)
- 비 유사성 계수 기반 약지도 객체 검출 (Dissimilarity Coefficient based Weakly Supervised Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1811.10016)
- 선택적 교차 도메인 정렬을 통한 객체 검출기 적응 (Adapting Object Detectors via Selective Cross-Domain Alignment) | \*\*[CVPR' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_CVPR\_2019/papers/Zhu\_Adapting\_Object\_Detectors\_via\_Selective\_Cross-Domain\_Alignment\_CVPR\_2019\_paper.pdf)
- 객체 검출을 위한 완전 양자화 네트워크 (Fully Quantized Network for Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://yan-junjie.github.io/publication/dblp-confcvprlilqwfy-19/dblp-confcvprlilqwfy-19.pdf)
- 세밀한 피처 모방을 활용한 객체 검출기 증류 (Distilling Object Detectors with Fine-grained Feature Imitation) | \*\*[CVPR' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_CVPR\_2019/papers/Wang\_Distilling\_Object\_Detectors\_With\_Fine-Grained\_Feature\_Imitation\_CVPR\_2019\_paper.pdf)
- 경계 박스 주석 재활용을 통한 멀티태스크 자기 지도 객체 검출 (Multi-task Self-Supervised Object Detection via Recycling of Bounding Box Annotations) | \*\*[CVPR' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_CVPR\_2019/papers/Lee\_Multi-Task\_Self-Supervised\_Object\_Detection\_via\_Recycling\_of\_Bounding\_Box\_Annotations\_CVPR\_2019\_paper.pdf)
- \*\*[Reasoning-RCNN]\*\* Reasoning-RCNN: 대규모 객체 검출에 적응형 글로벌 추론 통합 (Unifying Adaptive Global Reasoning into Large-scale Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_CVPR\_2019/papers/Xu\_Reasoning-RCNN\_Unifying\_Adaptive\_Global\_Reasoning\_Into\_Large-Scale\_Object\_Detection\_CVPR\_2019\_paper.pdf)
- 적응형 텍스트 영역 표현을 이용한 임의 형태 장면 텍스트 검출 (Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1905.05980.pdf)
- 활성화 보조 여진: 객체 검출기 개선을 위한 학습 기법 (Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://pdfs.semanticscholar.org/ec96/b6ae95e1ebbe4f7c0252301ede26dfc79467.pdf)
- 대규모 객체 검출을 위한 공간 인식 그래프 관계 네트워크 (Spatial-aware Graph Relation Network for Large-scale Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_CVPR\_2019/papers/Xu\_Spatial-Aware\_Graph\_Relation\_Network\_for\_Large-Scale\_Object\_Detection\_CVPR\_2019\_paper.pdf)
- \*\*[MaxpoolNMS]\*\* MaxpoolNMS: 2단계 객체 검출기에서 NMS 병목 현상 제거 (Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors) | \*\*[CVPR' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_CVPR\_2019/papers/Cai\_MaxpoolNMS\_Getting\_Rid\_of\_NMS\_Bottlenecks\_in\_Two-Stage\_Object\_Detectors\_CVPR\_2019\_paper.pdf)
- 심은 대로 거두리라: 약지도 객체 검출을 위한 고정밀 객체 제안 생성 (You reap what you sow: Generating High Precision Object Proposals for Weakly-supervised Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://web.cs.ucdavis.edu/~yjlee/projects/cvpr2019-youreapwhatyousow.pdf)
- 위치 인식 변형 가능한 합성곱 및 역방향 어텐션 필터링을 사용한 객체 검출 (Object detection with location-aware deformable convolution and backward attention filtering) | \*\*[CVPR' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_CVPR\_2019/papers/Zhang\_Object\_Detection\_With\_Location-Aware\_Deformable\_Convolution\_and\_Backward\_Attention\_Filtering\_CVPR\_2019\_paper.pdf)
- 다양화 및 매칭: 객체 검출을 위한 도메인 적응형 표현 학습 패러다임 (Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1905.05396.pdf)
- 인스턴스 분할을 위한 하이브리드 태스크 캐스케이드 (Hybrid Task Cascade for Instance Segmentation) | \*\*[CVPR' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1901.07518.pdf)
- \*\*[GFR]\*\* 게이트 피처 재사용을 통한 처음부터의 객체 검출 성능 개선 (Improving Object Detection from Scratch via Gated Feature Reuse) | \*\*[BMVC' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1712.00886v2.pdf) | [`[official code - pytorch]`](https://github.com/szq0214/GFR-DSOD)
- \*\*[Cascade RetinaNet]\*\* Cascade RetinaNet: 단일 단계 객체 검출의 일관성 유지 (Maintaining Consistency for Single-Stage Object Detection) | \*\*[BMVC' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1907.06881v1.pdf)
- 강인한 객체 검출을 위한 소프트 샘플링 (Soft Sampling for Robust Object Detection) | \*\*[BMVC' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1806.06986v2.pdf)
- 제한 없는 객체 검출을 위한 다중 적대적 Faster-RCNN (Multi-adversarial Faster-RCNN for Unrestricted Object Detection) | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1907.10343v1.pdf)
- 적대적으로 강인한 객체 검출을 향하여 (Towards Adversarially Robust Object Detection) | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1907.

10310v1.pdf)
- 도메인 적응형 객체 검출을 위한 강인한 학습 접근법 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.02361.pdf)
- 비디오 객체 검출을 위한 지연 메트릭: Average Precision이 말해주지 않는 것들 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.06368.pdf)
- 무인 항공기의 강건한 객체 검출 탐구: 딥 누이산스 분리 접근법 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.03856.pdf)
- 현저성 객체 검출을 위한 딥 파트-객체 관계 활용 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Liu\_Employing\_Deep\_Part-Object\_Relationships\_for\_Salient\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- 단일 샷 객체 검출을 위한 고속 고성능 특징 학습 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Wang\_Learning\_Rich\_Features\_at\_High-Speed\_for\_Single-Shot\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- 현저성 객체 검출을 위한 결합된 딥 특징 및 예측 정제의 구조적 모델링 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.04366.pdf)
- 선택성 또는 불변성: 경계 인식 현저성 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1812.10066.pdf)
- 비디오 객체 검출을 위한 점진적 희소 로컬 어텐션 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1903.09126.pdf)
- 비디오 기반 최소 지연 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.11092.pdf)
- 잠재 구조 전개를 통한 해석 가능한 객체 검출을 향하여 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Wu\_Towards\_Interpretable\_Object\_Detection\_by\_Unfolding\_Latent\_Structures\_ICCV\_2019\_paper.pdf)
- 분류 가중치 전송을 통한 객체 검출 스케일링 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.06804.pdf)
- \*\*[TridentNet]\*\* 객체 검출을 위한 스케일 인식 Trident Networks | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1901.01892.pdf)
- 소규모 데이터 객체 검출을 위한 생성 모델링 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Liu\_Generative\_Modeling\_for\_Small-Data\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- 제로 샷 객체 검출을 위한 변환 학습 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://salman-h-khan.github.io/papers/ICCV19-2.pdf)
- 비지도 도메인 적응형 원스테이지 객체 검출을 위한 자기 훈련 및 적대적 백그라운드 정규화 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.00597.pdf)
- \*\*[CenterNet]\*\* CenterNet: 객체 검출을 위한 키포인트 삼중항 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.08189.pdf)
- \*\*[DAFS]\*\* 단일 샷 객체 검출을 위한 동적 앵커 특징 선택 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://www4.comp.polyu.edu.hk/~cslzhang/paper/ICCV-DAFS.pdf)
- \*\*[Auto-FPN]\*\* Auto-FPN: 분류를 넘어선 객체 검출을 위한 자동 네트워크 아키텍처 적응 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Xu\_Auto-FPN\_Automatic\_Network\_Architecture\_Adaptation\_for\_Object\_Detection\_Beyond\_Classification\_ICCV\_2019\_paper.pdf)
- 제한 없는 객체 검출을 위한 다중 적대적 Faster-RCNN | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1907.10343.pdf)
- 비디오 객체 검출을 위한 객체 유도 외부 메모리 네트워크 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Deng\_Object\_Guided\_External\_Memory\_Network\_for\_Video\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- \*\*[ThunderNet]\*\* ThunderNet: 모바일 기기에서의 실시간 일반 객체 검출을 향하여 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1903.11752.pdf)
- \*\*[RDN]\*\* 비디오 객체 검출을 위한 관계 증류 네트워크 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://ar

xiv.org/pdf/1908.09511.pdf)
- \*\*[MMNet]\*\* 압축 영상에서의 빠른 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1811.11057.pdf)
- 고해상도 두드러진 객체 검출을 향하여 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.07274.pdf)
- \*\*[SCAN]\*\* 엣지 인지 두드러진 객체 검출을 위한 적층형 교차 정제 네트워크 | \*\*[ICCV' 19]\*\* |[`[official code]`](https://github.com/wuzhe71/SCAN) |[`[pdf]`]()
- 비디오 두드러진 객체 검출을 위한 모션 유도 어텐션 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.07061.pdf)
- 의사 레이블을 이용한 준지도 비디오 두드러진 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.04051.pdf)
- 객체 검출을 위한 제안 학습 및 순위화 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Tan\_Learning\_to\_Rank\_Proposals\_for\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- \*\*[WSOD2]\*\* WSOD2: 약지도 객체 검출을 위한 상향식 및 하향식 객체성 증류 학습 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.04972.pdf)
- \*\*[ClusDet]\*\* 항공 이미지에서의 군집화된 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.08008.pdf)
- 정밀한 엔드투엔드 약지도 객체 검출 네트워크를 향하여 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Yang\_Towards\_Precise\_End-to-End\_Weakly\_Supervised\_Object\_Detection\_Network\_ICCV\_2019\_paper.pdf)
- 피처 리웨이팅을 통한 퓨샷 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1812.01866.pdf)
- \*\*[Objects365]\*\* Objects365: 객체 검출을 위한 대규모 고품질 데이터셋 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Shao\_Objects365\_A\_Large-Scale\_High-Quality\_Dataset\_for\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- \*\*[EGNet]\*\* EGNet: 두드러진 객체 검출을 위한 엣지 가이드 네트워크 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.08297.pdf)
- 임계값 없는 두드러진 객체 검출을 위한 F-메이저 최적화 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1805.07567.pdf)
- 비디오 객체 검출을 위한 시퀀스 레벨 시맨틱 집계 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1907.06390.pdf)
- \*\*[NOTE-RCNN]\*\* NOTE-RCNN: 준지도 객체 검출을 위한 노이즈 허용 앙상블 RCNN | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1812.00124.pdf)
- 객체 검출을 위한 강화된 피처 가이드 정제 네트워크 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Nie\_Enriched\_Feature\_Guided\_Refinement\_Network\_for\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- \*\*[POD]\*\* POD: 스케일 민감 네트워크를 이용한 실용적 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.02225.pdf)
- \*\*[FCOS]\*\* FCOS: 완전 합성곱 단일 단계 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.01355.pdf)
- \*\*[RepPoints]\*\* RepPoints: 객체 검출을 위한 포인트 세트 표현 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.11490.pdf)
- 더 잘 따르고, 더 잘 되기 위해 따르기: 소형 객체 검출을 위한 피처 초해상도의 정밀한 지도 학습을 향하여 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Noh\_Better\_to\_Follow\_Follow\_to\_Be\_Better\_Towards\_Precise\_Supervision\_ICCV\_2019\_paper.pdf)
- 세분화 협업을 이용한 약지도 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.00551.pdf)
- 비디오 객체 검출을 위한 제안 간 장거리 시간적 관계 활용 | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Shvets\_Leveraging\_Long-Range\_Temporal\_Relationships\_Between\_Proposals\_for\_Video\_Object\_Detection\_ICCV\_2019\_paper.pdf)
- 검출

ing 11K Classes: 세밀한 경계 박스 없는 대규모 객체 검출 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.05217.pdf)
- \*\*[C-MIDN]\*\* C-MIDN: 약지도 객체 검출을 위한 분할 안내가 포함된 결합형 다중 인스턴스 검출 네트워크 | \*\*[ICCV' 19]\*\* |[`[pdf]`]()
- Meta-Learning to Detect Rare Objects | \*\*[ICCV' 19]\*\* |[`[pdf]`](http://openaccess.thecvf.com/content\_ICCV\_2019/papers/Wang\_Meta-Learning\_to\_Detect\_Rare\_Objects\_ICCV\_2019\_paper.pdf)
- \*\*[Cap2Det]\*\* Cap2Det: 객체 검출을 위한 약한 캡션 감독 증폭 학습 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1907.10164v1.pdf)
- \*\*[Gaussian YOLOv3]\*\* Gaussian YOLOv3: 자율 주행을 위한 위치 불확실성 기반 정확하고 빠른 객체 검출기 | \*\*[ICCV' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.04620.pdf) [`[official code - c]`](https://github.com/jwchoi384/Gaussian\_YOLOv3)
- \*\*[FreeAnchor]\*\* FreeAnchor: 시각적 객체 검출을 위한 앵커 매칭 학습 | \*\*[NeurIPS' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.02466v1.pdf)
- Memory-oriented Decoder for Light Field Salient Object Detection | \*\*[NeurIPS' 19]\*\* |[`[pdf]`](http://papers.nips.cc/paper/8376-memory-oriented-decoder-for-light-field-salient-object-detection.pdf)
- One-Shot Object Detection with Co-Attention and Co-Excitation | \*\*[NeurIPS' 19]\*\* |[`[pdf]`](http://papers.nips.cc/paper/8540-one-shot-object-detection-with-co-attention-and-co-excitation.pdf)
- \*\*[DetNAS]\*\* DetNAS: 객체 검출을 위한 백본 탐색 | \*\*[NeurIPS' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1903.10979v4.pdf)
- Consistency-based Semi-supervised Learning for Object detection | \*\*[NeurIPS' 19]\*\* |[`[pdf]`](https://papers.nips.cc/paper/9259-consistency-based-semi-supervised-learning-for-object-detection.pdf)
- \*\*[NATS]\*\* Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection | \*\*[NeurIPS' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.02293.pdf)
- \*\*[AA]\*\* Learning Data Augmentation Strategies for Object Detection | \*\*[arXiv' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1906.11172.pdf)
- \*\*[Spinenet]\*\* Spinenet: Learning scale-permuted backbone for recognition and localization | \*\*[arXiv' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.05027.pdf)
- 객체 검출 20년 역사: 서베이 논문 | \*\*[arXiv' 19]\*\* |[`[pdf]`](https://arxiv.org/pdf/1905.05055.pdf)
## 2020
- \*\*[Spiking-YOLO]\*\* Spiking-YOLO: 실시간 객체 검출을 위한 스파이킹 신경망 | \*\*[AAAI' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1903.06530.pdf)
- Tell Me What They're Holding: Weakly-supervised Object Detection with Transferable Knowledge from Human-object Interaction | \*\*[AAAI' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1911.08141v1.pdf)
- \*\*[CBnet]\*\* Cbnet: 객체 검출을 위한 새로운 복합 백본 네트워크 구조 | \*\*[AAAI' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1909.03625.pdf)
- \*\*[Distance-IoU Loss]\*\* Distance-IoU Loss: 경계 박스 회귀를 위한 더 빠르고 나은 학습 | \*\*[AAAI' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1911.08287v1.pdf)
- Computation Reallocation for Object Detection | \*\*[ICLR' 20]\*\* |[`[pdf]`](https://openreview.net/pdf?id=SkxLFaNKwB)
- \*\*[YOLOv4]\*\* YOLOv4: 객체 검출의 최적 속도와 정확도 | \*\*[arXiv' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2004.10934.pdf)
- Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1908.01998.pdf)
- Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2005.08455.pdf)
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.02424.pdf)
- Rethinking Classification and Localization for Object Detection | \*\*[CVPR' 20]\*\*

*\* |[`[pdf]`](https://arxiv.org/pdf/1904.06493.pdf)
- 시각적 객체 검출을 위한 다중 앵커 학습 (Multiple Anchor Learning for Visual Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.02252.pdf)
- \*\*[CentripetalNet]\*\* CentripetalNet: 객체 검출을 위한 고품질 키포인트 쌍 추구 (Pursuing High-Quality Keypoint Pairs for Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.09119.pdf)
- 1단계 객체 검출을 위한 노이즈가 있는 앵커로부터의 학습 (Learning From Noisy Anchors for One-Stage Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.05086.pdf)
- \*\*[EfficientDet]\*\* EfficientDet: 확장 가능하고 효율적인 객체 검출 (Scalable and Efficient Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1911.09070.pdf)
- 균형 잡힌 그룹 소프트맥스를 이용한 롱테일 객체 검출의 분류기 불균형 극복 (Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Li\_Overcoming\_Classifier\_Imbalance\_for\_Long-Tail\_Object\_Detection\_With\_Balanced\_Group\_CVPR\_2020\_paper.pdf)
- 방향성 및 조밀하게 배치된 객체 검출을 위한 동적 정제 네트워크 (Dynamic Refinement Network for Oriented and Densely Packed Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2005.09973.pdf)
- 노이즈 인지 완전 웹 기반 지도학습 객체 검출 (Noise-Aware Fully Webly Supervised Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Shen\_Noise-Aware\_Fully\_Webly\_Supervised\_Object\_Detection\_CVPR\_2020\_paper.pdf)
- \*\*[Hit-Detector]\*\* Hit-Detector: 객체 검출을 위한 계층적 삼위일체 아키텍처 탐색 (Hierarchical Trinity Architecture Search for Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.11818.pdf)
- \*\*[D2Det]\*\* D2Det: 고품질 객체 검출 및 인스턴스 세분화를 향하여 (Towards High Quality Object Detection and Instance Segmentation) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Cao\_D2Det\_Towards\_High\_Quality\_Object\_Detection\_and\_Instance\_Segmentation\_CVPR\_2020\_paper.pdf)
- 객체 검출에서의 프라임 샘플 어텐션 (Prime Sample Attention in Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1904.04821.pdf)
- 한 번도 보지 말 것: 제로샷 검출을 위한 특징 합성 (Don’t Even Look Once: Synthesizing Features for Zero-Shot Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1911.07933.pdf)
- 도메인 적응형 객체 검출을 위한 범주형 정규화 탐색 (Exploring Categorical Regularization for Domain Adaptive Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.09152.pdf)
- \*\*[SP-NAS]\*\* SP-NAS: 객체 검출을 위한 직렬-병렬 백본 탐색 (Serial-to-Parallel Backbone Search for Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Jiang\_SP-NAS\_Serial-to-Parallel\_Backbone\_Search\_for\_Object\_Detection\_CVPR\_2020\_paper.pdf)
- \*\*[NAS-FCOS]\*\* NAS-FCOS: 객체 검출을 위한 빠른 신경 아키텍처 탐색 (Fast Neural Architecture Search for Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1906.04423.pdf)
- \*\*[DR Loss]\*\* DR Loss: 분포 순위를 통한 객체 검출 성능 향상 (Improving Object Detection by Distributional Ranking) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1907.10156.pdf)
- 붐비는 장면에서의 검출: 하나의 제안, 다중 예측 (Detection in Crowded Scenes: One Proposal, Multiple Predictions) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.09163.pdf)
- \*\*[AugFPN]\*\* AugFPN: 객체 검출을 위한 멀티 스케일 특징 학습 개선 (Improving Multi-Scale Feature Learning for Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.05384.pdf)
- 문맥 인지 합성 넷을 이용한 가림 속 강인한 객체 검출 (Robust Object Detection Under Occlusion With Context-Aware CompositionalNets) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Wang\_Robust\_Object\_Detection\_Under\_Occlusion\_With\_Context-Aware\_CompositionalNets\_CVPR\_2020\_paper.pdf)
- 크로스 도메인 문서 객체 검출: 벤치마크 스위트 및 방법 (Cross-Domain Document Object Detection: Benchmark Suite and Method) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.13197.pdf)
- 웹 기반 지도학습 객체 검출을 위한 어텐티브 학습과 상향식 및 하향식 단서 탐색 (Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly Supervised Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.09790.pdf)
- \*\*[SLV]\*\* SLV: 약지도 객체 검출을 위한 공간 우도 투표 (Spatial Likelihood Voting for Weakly Supervised Object Detection) | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Chen\_SLV\_Spatial\_Likelihood\_Voting\_for\_Weakly\_Supervised\_Object\_Detection\_CVPR\_2020\_paper.pdf)
- \*\*[HAMBox]\*\* HAMBox: 얼굴 검출에서 고품질 앵커 마이닝 파고들기 (Delving Into Mining High-Quality Anchors on Face Detection) |

\*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.09231.pdf)
- \*\*[Context R-CNN]\*\* Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.03538.pdf)
- Mixture Dense Regression for Object Detection and Human Pose Estimation | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.00821.pdf)
- Offset Bin Classification Network for Accurate Object Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Qiu\_Offset\_Bin\_Classification\_Network\_for\_Accurate\_Object\_Detection\_CVPR\_2020\_paper.pdf)
- \*\*[NETNet]\*\* NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2001.06690.pdf)
- Scale-Equalizing Pyramid Convolution for Object Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2005.03101.pdf)
- Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://cse.buffalo.edu/~jsyuan/papers/2020/TFAN.pdf)
- \*\*[MnasFPN]\*\* MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.01106.pdf)
- Physically Realizable Adversarial Examples for LiDAR Object Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2004.00543.pdf)
- Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.10275.pdf)
- Incremental Few-Shot Object Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.04668.pdf)
- Where, What, Whether: Multi-Modal Learning Meets Pedestrian Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Luo\_Where\_What\_Whether\_Multi-Modal\_Learning\_Meets\_Pedestrian\_Detection\_CVPR\_2020\_paper.pdf)
- Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.11303.pdf)
- Learning a Unified Sample Weighting Network for Object Detection | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://openaccess.thecvf.com/content\_CVPR\_2020/papers/Cai\_Learning\_a\_Unified\_Sample\_Weighting\_Network\_for\_Object\_Detection\_CVPR\_2020\_paper.pdf)
- Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization | \*\*[CVPR' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.12290.pdf)
- DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution | \*\*[arXiv' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2006.02334v1.pdf)
- \*\*[DETR]\*\* End-to-End Object Detection with Transformers | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2005.12872.pdf)
- Suppress and Balance: A Simple Gated Network for Salient Object Detection | \*\*[ECCV' 20]\*\* |[`[code]`](https://github.com/Xiaoqi-Zhao-DLUT/GateNet-RGB-Saliency)
- \*\*[BorderDet]\*\* BorderDet: Border Feature for Dense Object Detection | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.11056.pdf)
- Corner Proposal Network for Anchor-free, Two-stage Object Detection | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.13816.pdf)
- A General Toolbox for Understanding Errors in Object Detection | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2008.08115v1.pdf)
- \*\*[Chained-Tracker]\*\* Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.14557.pdf)
- Side-Aware Boundary Localization for More Precise Object Detection | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.04260.pdf)
- \*\*[PIoU]\*\* PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.09584.pdf)
- \*\*[AABO]\*\* AABO: Adaptive Anchor Box Optimization for Object

베이지안 서브샘플링을 통한 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.09336.pdf)
- 100K 파라미터를 사용한 고효율 중요 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.05643.pdf)
- \*\*[GeoGraph]\*\* GeoGraph: 기하학적 단서를 이용한 그래프 기반 다중 시점 객체 탐지 엔드투엔드 학습 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.10151.pdf)
- 저샷에서 다중샷으로: 객체 탐지를 위한 혼합 지도 학습 기반 어노테이션 기법 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2008.09694.pdf)
- 더 저렴한 사전 학습 런치: 객체 탐지를 위한 효율적인 패러다임 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2004.12178.pdf)
- 원형 스무스 라벨을 이용한 임의 방향 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.05597.pdf)
- 소프트 앵커 포인트 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1911.12448.pdf)
- 여러 데이터셋의 통합 라벨 공간을 이용한 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2008.06614.pdf)
- \*\*[MimicDet]\*\* MimicDet: 원스테이지와 투스테이지 객체 탐지 간의 격차 해소 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://www.ecva.net/papers/eccv\_2020/papers\_ECCV/papers/123590528.pdf)
- 안개 및 우천 환경을 위한 사전 지식 기반 도메인 적응형 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.00070.pdf)
- \*\*[Dynamic R-CNN]\*\* Dynamic R-CNN: 동적 학습을 통한 고품질 객체 탐지 향상 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2004.06002.pdf)
- \*\*[OS2D]\*\* OS2D: 앵커 피처 매칭을 통한 원스테이지 원샷 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.06800.pdf)
- 퓨샷 객체 탐지를 위한 다중 스케일 긍정 샘플 개선 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.09384.pdf)
- 야외 객체를 위한 퓨샷 객체 탐지 및 시점 추정 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.12107.pdf)
- 도메인 적응형 객체 탐지를 위한 영역 제안 localization과 classification 간의 협업 학습 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2009.08119.pdf)
- 커넥토믹스의 대규모 객체 탐지를 위한 투스트림 능동 쿼리 제안 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://donglaiw.github.io/paper/2020\_eccv\_twostream.pdf)
- \*\*[FDTS]\*\* FDTS: 객체 탐지 및 그 이상을 위한 빠른 다양성 변환 탐색 | \*\*[ECCV' 20]\*\*
- 듀얼 리프리인먼트 수중 객체 탐지 네트워크 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://www.ecva.net/papers/eccv\_2020/papers\_ECCV/papers/123650273.pdf)
- \*\*[APRICOT]\*\* APRICOT: 객체 탐지에 대한 물리적 적대적 공격 데이터셋 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/1912.08166.pdf)
- 객체 탐지를 위한 대규모 배치 최적화: 12분 만에 COCO 학습하기 | \*\*[ECCV' 20]\*\* |[`[pdf]`](http://www.ecva.net/papers/eccv\_2020/papers\_ECCV/papers/123660477.pdf)
- 영역 기반 객체 탐지를 위한 계층적 컨텍스트 임베딩 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2008.01338.pdf)
- 자율 주행을 위한 필러 기반 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.10323.pdf)
- 객체 탐지를 위해 박스 더 깊게 파헤치기 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.14350.pdf)
- 비대칭 삼각 방향 Faster-RCNN을 통한 도메인 적응형 객체 탐지 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.01571.pdf)
- 객체 탐지를 위한 IoU 예측 기반 확률적 앵커 할당 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.08103.pdf)
- \*\*[HoughNet]\*\* HoughNet: 상향식 객체 탐지를 위한 근거리 및 원거리 증거 통합 | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.02355.pdf)
- \*\*[LabelEnc]\*\* LabelEnc: 객체 탐지를 위한 새로운 중간 지도 학습 방법 | \*\*[ECCV' 20]\*\* |

[`[pdf]`](https://arxiv.org/pdf/2007.03282.pdf)
- Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.07986.pdf)
- On the Importance of Data Augmentation for Object Detection | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/abs/1906.11172)
- Adaptive Object Detection with Dual Multi-Label Prediction | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2003.12943.pdf)
- Quantum-soft QUBO Suppression for Accurate Object Detection | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.13992.pdf)
- Improving Object Detection with Selective Self-supervised Self-training | \*\*[ECCV' 20]\*\* |[`[pdf]`](https://arxiv.org/pdf/2007.09162.pdf)
##
## Dataset Papers
자주 사용되는 객체 검출(Object Detection) 데이터셋의 통계입니다. 표는 [이 서베이 논문](https://arxiv.org/pdf/1809.02165v1.pdf)에서 가져왔습니다.

| 챌린지 | 객체 클래스 | 이미지 수 | | | 어노테이션된 이미지 수 | |
| --- | --- | --- | --- | --- | --- | --- |
| Train | Val | Test | Train | Val |
| PASCAL VOC 객체 검출 챌린지 | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| VOC07 | 20 | 2,501 | 2,510 | 4,952 | 6,301 (7,844) | 6,307 (7,818) |
| VOC08 | 20 | 2,111 | 2,221 | 4,133 | 5,082 (6,337) | 5,281 (6,347) |
| VOC09 | 20 | 3,473 | 3,581 | 6,650 | 8,505 (9,760) | 8,713 (9,779) |
| VOC10 | 20 | 4,998 | 5,105 | 9,637 | 11,577 (13,339) | 11,797 (13,352) |
| VOC11 | 20 | 5,717 | 5,823 | 10,994 | 13,609 (15,774) | 13,841 (15,787) |
| VOC12 | 20 | 5,717 | 5,823 | 10,991 | 13,609 (15,774) | 13,841 (15,787) |
| ILSVRC 객체 검출 챌린지 | | | | | | |
| ILSVRC13 | 200 | 395,909 | 20,121 | 40,152 | 345,854 | 55,502 |
| ILSVRC14 | 200 | 456,567 | 20,121 | 40,152 | 478,807 | 55,502 |
| ILSVRC15 | 200 | 456,567 | 20,121 | 51,294 | 478,807 | 55,502 |
| ILSVRC16 | 200 | 456,567 | 20,121 | 60,000 | 478,807 | 55,502 |
| ILSVRC17 | 200 | 456,567 | 20,121 | 65,500 | 478,807 | 55,502 |
| MS COCO 객체 검출 챌린지 | | | | | | |
| MS COCO15 | 80 | 82,783 | 40,504 | 81,434 | 604,907 | 291,875 |
| MS COCO16 | 80 | 82,783 | 40,504 | 81,434 | 604,907 | 291,875 |
| MS COCO17 | 80 | 118,287 | 5,000 | 40,670 | 860,001 | 36,781 |
| MS COCO18 | 80 | 118,287 | 5,000 | 40,670 | 860,001 | 36,781 |
| Open Images 객체 검출 챌린지 | | | | | | |
| OID18 | 500 | 1,743,042 | 41,620 | 125,436 | 12,195,144 | ― |

객체 검출에서 주로 사용되는 데이터셋과 관련된 논문은 다음과 같습니다.
- \*\*[PASCAL VOC]\*\* The PASCAL Visual Object Classes (VOC) Challenge | \*\*[IJCV' 10]\*\* | [`[pdf]`](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham10.pdf)
- \*\*[PASCAL VOC]\*\* The PASCAL Visual Object Classes Challenge: A Retrospective | \*\*[IJCV' 15]\*\* | [`[pdf]`](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham15.pdf) | [`[link]`](http://host.robots.ox.ac.uk/pascal/VOC/)
- \*\*[ImageNet]\*\* ImageNet: A Large-Scale Hierarchical Image Database| \*\*[CVPR' 09]\*\* | [`[pdf]`](http://www.image-net.org/papers/imagenet\_cvpr09.pdf)
- \*\*[ImageNet]\*\* ImageNet Large Scale Visual Recognition Challenge | \*\*[IJCV' 15]\*\* | [`[pdf]`](https://arxiv.org/pdf/1409.0575.pdf) | [`[link]`](http://www.image-net.org/challenges/LSVRC/)
- \*\*[COCO]\*\* Microsoft COCO: Common Objects in Context | \*\*[ECCV' 14]\*\* | [`[pdf]`](https://arxiv.org/pdf/1405.0312.pdf) | [`[link]`](http://cocodataset.org/)
- \*\*[Open Images]\*\* The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale | \*\*[arXiv' 18]\*\* | [`[pdf]`](https://arxiv.org/pdf/1811.00982v1.pdf) | [`[link]`](https://storage.googleapis.com/openimages/web/index.html)
- \*\*[DOTA]\*\* DOTA: A Large-scale Dataset for Object Detection in Aerial Images | \*\*[CVPR' 18]\*\* | [`[pdf]`](https://arxiv.org/pdf/1711.10398v3.pdf) | [`[link]`](https://captain-whu.github.io/DOTA/)
- \*\*[Objects365]\*\* Objects365: A Large-Scale, High-Quality Dataset for Object Detection | \*\*[ICCV' 19]\*\* | [`[link]`](https://www.biendata.com/competition/objects365/)
##
## Contact & Feedback
논문에 대한 제안 사항이 있으시면 언제든지 메일 주세요 :)
- [e-mail](mailto:Hoseong.Lee@cognex.com)
- [blog](https://hoya012.github.io/)
- [pull request](https://github.com/hoya012/deep\_learning\_object\_detection/pulls)

deep_learning_object_detection

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

deep_learning_object_detection

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README