ICCV2021目标检测方向论文

研究一下ICCV2021目标检测方向的论文。

完整的paper list：https://iccv2021.thecvf.com/sites/default/files/2021-10/paper%20list%20per%20session%2010-2.xlsx

[1] GraphFPN: Graph Feature Pyramid Network for Object Detection

paper: https://arxiv.org/abs/2108.00580

code: TBD

[2] SimROD: A Simple Adaptation Method for Robust Object Detection

paper: https://arxiv.org/abs/2107.13389

code: TBD

[3] Normalization Matters in Weakly Supervised Object Localization

paper: https://arxiv.org/abs/2107.13221

code: TBD

[4] Rank & Sort Loss for Object Detection and Instance Segmentation

paper: https://arxiv.org/abs/2107.11669

code: https://github.com/kemaloksuz/RankSortLoss

[5] DetCo: Unsupervised Contrastive Learning for Object Detection

paper: https://arxiv.org/abs/2102.04803

code: https://github.com/xieenze/DetCo

[6] Geometry Uncertainty Projection Network for Monocular 3D Object Detection

paper: https://arxiv.org/abs/2107.13774

code: TBD

[7] Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection

paper: https://arxiv.org/abs/2107.12664

code: TBD

[8] Active Learning for Deep Object Detection via Probabilistic Modeling

paper: https://arxiv.org/abs/2103.16130

code: TBD

[9] Detecting Invisible People

paper: https://arxiv.org/abs/2012.08419

project: Detecting Invisible People

[10] MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding

paper: https://arxiv.org/abs/2104.12763

code: https://github.com/ashkamath/mdetr

[11] TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization

paper: https://arxiv.org/abs/2103.14862

code: TBD

[12] Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

paper: https://arxiv.org/abs/2108.01499

code: https://github.com/DongSky/lbba_boosted_wsod

[13] Fast Convergence of DETR with Spatially Modulated Co-Attention

paper: https://arxiv.org/abs/2108.02404

code: https://github.com/gaopengcuhk/SMCA-DETR

[14] Disentangled High Quality Salient Object Detection

paper: https://arxiv.org/abs/2108.03551

code: TBD

[15] MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach

paper: https://arxiv.org/abs/2108.05060

code: TBD

[16] Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

paper: https://arxiv.org/abs/2108.05249

code: http://www.trace.ethz.ch/lidar_fog_simulation

[17] Oriented R-CNN for Object Detection

paper: https://arxiv.org/abs/2108.05699

code: https://github.com/jbwang1997/OBBDetection

[18] Conditional DETR for Fast Training Convergence

paper: https://arxiv.org/abs/2108.06152

code: https://git.io/ConditionalDETR

[19] RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection

paper: https://arxiv.org/abs/2108.07794

code: TBD

[20] G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation

paper: https://arxiv.org/abs/2108.07482

code: TBD

[21] LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector

paper: https://arxiv.org/abs/2108.08258

code: TBD

[22] DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection

paper: https://arxiv.org/abs/2108.09017

code: TBD

版权声明：本文为CSDN博主「一个菜鸟的奋斗」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/u013685264/article/details/119345087