CVPR2022目标检测方向论文

完整的paper list已经放出来了，可以直接查看。

https://cvpr2022.thecvf.com/sites/default/files/2022-04/accepted%20papers.xlsx
 

---

[1] SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection

paper: https://arxiv.org/pdf/2203.06398

code: https://github.com/CityU-AIM-Group/SIGMA

[2] Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection

paper: https://arxiv.org/pdf/2203.05787

code: TBD

[3] Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

paper: https://arxiv.org/pdf/2011.12001

code: https://github.com/qq456cvb/CanonicalVoting

[4] Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

paper: https://arxiv.org/pdf/2203.05238

code: https://github.com/xuxw98/BackToReality

[5] Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild

paper: https://arxiv.org/pdf/2203.03800

code: https://github.com/deeplearning-wisc/stud

[6] Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection

paper: https://arxiv.org/pdf/2203.02688

code: https://github.com/lartpang/ZoomNet

[7] DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

paper: https://arxiv.org/pdf/2203.01305

code: https://github.com/FengLi-ust/DN-DETR

[8] Localization Distillation for Dense Object Detection

paper: https://arxiv.org/pdf/2102.12252

code: GitHub - HikariTJU/LD: Localization Distillation for Dense Object Detection (CVPR 2022)

[9] Accelerating DETR Convergence via Semantic-Aligned Matching

paper: https://arxiv.org/pdf/2203.06883

code: GitHub - ZhangGongjie/SAM-DETR: Official PyTorch Implementation of SAM-DETR (CVPR 2022)

[10] Point Density-Aware Voxels for LiDAR 3D Object Detection

paper: https://arxiv.org/pdf/2203.05662

code: https://github.com/TRAILab/PDV

[11] Spatial Commonsense Graph for Object Localisation in Partial Scenes

paper: https://arxiv.org/pdf/2203.05380

code: Spatial Commonsense Graph for Object Localisation in Partial Scenes

[12] Adversarial Texture for Fooling Person Detectors in the Physical World

paper: https://arxiv.org/pdf/2203.03373

code: TBD

[13] Rethinking Efficient Lane Detection via Curve Modeling

paper: https://arxiv.org/pdf/2203.02431

code: GitHub - voldemortX/pytorch-auto-drive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, PRNet, RESA, LSTR, BézierLaneNet...) based on PyTorch with mixed precision training

[14] A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation

paper: https://arxiv.org/pdf/2203.02133

code: TBD

[15] Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving

paper: https://arxiv.org/pdf/2203.02112

code: GitHub - revisitq/Pseudo-Stereo-3D

[16] Weakly Supervised Object Localization as Domain Adaption

paper: https://arxiv.org/pdf/2203.01714

code: https://github.com/zh460045050/DA-WSOL_CVPR2022

[17] Focal and Global Knowledge Distillation for Detectors

paper: https://arxiv.org/pdf/2111.11837

code: GitHub - yzd-v/FGD: Focal and Global Knowledge Distillation for Detectors (CVPR 2022)