CVPR 2022 Open Access Repository

Learning With Limited Labelled Data for Image and Video Understanding

Unsupervised Salient Object Detection With Spectral Cluster Voting: Gyungin Shin,

Samuel Albanie,

Weidi Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shin_2022_CVPR, author = {Shin, Gyungin and Albanie, Samuel and Xie, Weidi}, title = {Unsupervised Salient Object Detection With Spectral Cluster Voting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3971-3980} }
TDT: Teaching Detectors To Track Without Fully Annotated Videos: Shuzhi Yu,

Guanhang Wu,

Chunhui Gu,

Mohammed E. Fathy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Shuzhi and Wu, Guanhang and Gu, Chunhui and Fathy, Mohammed E.}, title = {TDT: Teaching Detectors To Track Without Fully Annotated Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3940-3950} }
Efficient Conditional Pre-Training for Transfer Learning: Shuvam Chakraborty,

Burak Uzkent,

Kumar Ayush,

Kumar Tanmay,

Evan Sheehan,

Stefano Ermon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chakraborty_2022_CVPR, author = {Chakraborty, Shuvam and Uzkent, Burak and Ayush, Kumar and Tanmay, Kumar and Sheehan, Evan and Ermon, Stefano}, title = {Efficient Conditional Pre-Training for Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4241-4250} }
CDAD: A Common Daily Action Dataset With Collected Hard Negative Samples: Wangmeng Xiang,

Chao Li,

Ke Li,

Biao Wang,

Xian-sheng Hua,

Lei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Xiang_2022_CVPR, author = {Xiang, Wangmeng and Li, Chao and Li, Ke and Wang, Biao and Hua, Xian-sheng and Zhang, Lei}, title = {CDAD: A Common Daily Action Dataset With Collected Hard Negative Samples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3921-3930} }
Towards Open-Set Object Detection and Discovery: Jiyang Zheng,

Weihao Li,

Jie Hong,

Lars Petersson,

Nick Barnes; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2022_CVPR, author = {Zheng, Jiyang and Li, Weihao and Hong, Jie and Petersson, Lars and Barnes, Nick}, title = {Towards Open-Set Object Detection and Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3961-3970} }
SCVRL: Shuffled Contrastive Video Representation Learning: Michael Dorkenwald,

Fanyi Xiao,

Biagio Brattoli,

Joseph Tighe,

Davide Modolo; [pdf] [arXiv]
[bibtex]
@InProceedings{Dorkenwald_2022_CVPR, author = {Dorkenwald, Michael and Xiao, Fanyi and Brattoli, Biagio and Tighe, Joseph and Modolo, Davide}, title = {SCVRL: Shuffled Contrastive Video Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4132-4141} }
Denoising Pretraining for Semantic Segmentation: Emmanuel Asiedu Brempong,

Simon Kornblith,

Ting Chen,

Niki Parmar,

Matthias Minderer,

Mohammad Norouzi; [pdf] [arXiv]
[bibtex]
@InProceedings{Brempong_2022_CVPR, author = {Brempong, Emmanuel Asiedu and Kornblith, Simon and Chen, Ting and Parmar, Niki and Minderer, Matthias and Norouzi, Mohammad}, title = {Denoising Pretraining for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4175-4186} }
Contrastive Regularization for Semi-Supervised Learning: Doyup Lee,

Sungwoong Kim,

Ildoo Kim,

Yeongjae Cheon,

Minsu Cho,

Wook-Shin Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Doyup and Kim, Sungwoong and Kim, Ildoo and Cheon, Yeongjae and Cho, Minsu and Han, Wook-Shin}, title = {Contrastive Regularization for Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3911-3920} }
ViTOL: Vision Transformer for Weakly Supervised Object Localization: Saurav Gupta,

Sourav Lakhotia,

Abhay Rawat,

Rahul Tallamraju; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2022_CVPR, author = {Gupta, Saurav and Lakhotia, Sourav and Rawat, Abhay and Tallamraju, Rahul}, title = {ViTOL: Vision Transformer for Weakly Supervised Object Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4101-4110} }
Consistency-Based Active Learning for Object Detection: Weiping Yu,

Sijie Zhu,

Taojiannan Yang,

Chen Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Weiping and Zhu, Sijie and Yang, Taojiannan and Chen, Chen}, title = {Consistency-Based Active Learning for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3951-3960} }
CFA: Constraint-Based Finetuning Approach for Generalized Few-Shot Object Detection: Karim Guirguis,

Ahmed Hendawy,

George Eskandar,

Mohamed Abdelsamad,

Matthias Kayser,

Jürgen Beyerer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guirguis_2022_CVPR, author = {Guirguis, Karim and Hendawy, Ahmed and Eskandar, George and Abdelsamad, Mohamed and Kayser, Matthias and Beyerer, J\"urgen}, title = {CFA: Constraint-Based Finetuning Approach for Generalized Few-Shot Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4039-4049} }
Attention Consistency on Visual Corruptions for Single-Source Domain Generalization: Ilke Cugu,

Massimiliano Mancini,

Yanbei Chen,

Zeynep Akata; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cugu_2022_CVPR, author = {Cugu, Ilke and Mancini, Massimiliano and Chen, Yanbei and Akata, Zeynep}, title = {Attention Consistency on Visual Corruptions for Single-Source Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4165-4174} }
Few-Shot Class Incremental Learning Leveraging Self-Supervised Features: Touqeer Ahmad,

Akshay Raj Dhamija,

Steve Cruz,

Ryan Rabinowitz,

Chunchun Li,

Mohsen Jafarzadeh,

Terrance E. Boult; [pdf] [supp]
[bibtex]
@InProceedings{Ahmad_2022_CVPR, author = {Ahmad, Touqeer and Dhamija, Akshay Raj and Cruz, Steve and Rabinowitz, Ryan and Li, Chunchun and Jafarzadeh, Mohsen and Boult, Terrance E.}, title = {Few-Shot Class Incremental Learning Leveraging Self-Supervised Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3900-3910} }
Faster, Lighter, Robuster: A Weakly-Supervised Crowd Analysis Enhancement Network and a Generic Feature Extraction Framework: Shaokai Wu,

Zhaogeng Liu,

Wencheng Pei,

Jianbo Hong,

Zhanshan Li; [pdf]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Shaokai and Liu, Zhaogeng and Pei, Wencheng and Hong, Jianbo and Li, Zhanshan}, title = {Faster, Lighter, Robuster: A Weakly-Supervised Crowd Analysis Enhancement Network and a Generic Feature Extraction Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4050-4059} }
Few-Shot Supervised Prototype Alignment for Pedestrian Detection on Fisheye Images: Thaddäus Wiedemer,

Stefan Wolf,

Arne Schumann,

Kaisheng Ma,

Jürgen Beyerer; [pdf] [supp]
[bibtex]
@InProceedings{Wiedemer_2022_CVPR, author = {Wiedemer, Thadd\"aus and Wolf, Stefan and Schumann, Arne and Ma, Kaisheng and Beyerer, J\"urgen}, title = {Few-Shot Supervised Prototype Alignment for Pedestrian Detection on Fisheye Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4142-4153} }
Auxiliary Learning for Self-Supervised Video Representation via Similarity-Based Knowledge Distillation: Amirhossein Dadashzadeh,

Alan Whone,

Majid Mirmehdi; [pdf] [arXiv]
[bibtex]
@InProceedings{Dadashzadeh_2022_CVPR, author = {Dadashzadeh, Amirhossein and Whone, Alan and Mirmehdi, Majid}, title = {Auxiliary Learning for Self-Supervised Video Representation via Similarity-Based Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4231-4240} }
Open-Set Domain Adaptation Under Few Source-Domain Labeled Samples: Sayan Rakshit,

Balasubramanian S,

Hmrishav Bandyopadhyay,

Piyush Bharambe,

Sai Nandan Desetti,

Biplab Banerjee,

Subhasis Chaudhuri; [pdf] [supp]
[bibtex]
@InProceedings{Rakshit_2022_CVPR, author = {Rakshit, Sayan and S, Balasubramanian and Bandyopadhyay, Hmrishav and Bharambe, Piyush and Desetti, Sai Nandan and Banerjee, Biplab and Chaudhuri, Subhasis}, title = {Open-Set Domain Adaptation Under Few Source-Domain Labeled Samples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4029-4038} }
CoDo: Contrastive Learning With Downstream Background Invariance for Detection: Bing Zhao,

Jun Li,

Hong Zhu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Bing and Li, Jun and Zhu, Hong}, title = {CoDo: Contrastive Learning With Downstream Background Invariance for Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4196-4201} }
Bootstrapped Representation Learning for Skeleton-Based Action Recognition: Olivier Moliner,

Sangxia Huang,

Kalle Åström; [pdf]
[bibtex]
@InProceedings{Moliner_2022_CVPR, author = {Moliner, Olivier and Huang, Sangxia and \r{A}str\"om, Kalle}, title = {Bootstrapped Representation Learning for Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4154-4164} }
Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction: Brandon Leung,

Chih-Hui Ho,

Nuno Vasconcelos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Leung_2022_CVPR, author = {Leung, Brandon and Ho, Chih-Hui and Vasconcelos, Nuno}, title = {Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4080-4090} }
AuxMix: Semi-Supervised Learning With Unconstrained Unlabeled Data: Amin Banitalebi-Dehkordi,

Pratik Gujjar,

Yong Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Banitalebi-Dehkordi_2022_CVPR, author = {Banitalebi-Dehkordi, Amin and Gujjar, Pratik and Zhang, Yong}, title = {AuxMix: Semi-Supervised Learning With Unconstrained Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3999-4006} }
Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity: Nanqing Dong,

Jiayi Wang,

Irina Voiculescu; [pdf] [arXiv]
[bibtex]
@InProceedings{Dong_2022_CVPR, author = {Dong, Nanqing and Wang, Jiayi and Voiculescu, Irina}, title = {Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4212-4220} }
Uniform Priors for Data-Efficient Learning: Samarth Sinha,

Karsten Roth,

Anirudh Goyal,

Marzyeh Ghassemi,

Zeynep Akata,

Hugo Larochelle,

Animesh Garg; [pdf]
[bibtex]
@InProceedings{Sinha_2022_CVPR, author = {Sinha, Samarth and Roth, Karsten and Goyal, Anirudh and Ghassemi, Marzyeh and Akata, Zeynep and Larochelle, Hugo and Garg, Animesh}, title = {Uniform Priors for Data-Efficient Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4017-4028} }
Cluster-To-Adapt: Few Shot Domain Adaptation for Semantic Segmentation Across Disjoint Labels: Tarun Kalluri,

Manmohan Chandraker; [pdf]
[bibtex]
@InProceedings{Kalluri_2022_CVPR, author = {Kalluri, Tarun and Chandraker, Manmohan}, title = {Cluster-To-Adapt: Few Shot Domain Adaptation for Semantic Segmentation Across Disjoint Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4121-4131} }
Self-Supervised Learning of Pose-Informed Latents: Raphaël Jean,

Pierre-Luc St-Charles,

Sören Pirk,

Simon Brodeur; [pdf] [supp]
[bibtex]
@InProceedings{Jean_2022_CVPR, author = {Jean, Rapha\"el and St-Charles, Pierre-Luc and Pirk, S\"oren and Brodeur, Simon}, title = {Self-Supervised Learning of Pose-Informed Latents}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4007-4016} }
Transformaly - Two (Feature Spaces) Are Better Than One: Matan Jacob Cohen,

Shai Avidan; [pdf] [supp]
[bibtex]
@InProceedings{Cohen_2022_CVPR, author = {Cohen, Matan Jacob and Avidan, Shai}, title = {Transformaly - Two (Feature Spaces) Are Better Than One}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4060-4069} }
Vicinal Counting Networks: Viresh Ranjan,

Minh Hoai; [pdf]
[bibtex]
@InProceedings{Ranjan_2022_CVPR, author = {Ranjan, Viresh and Hoai, Minh}, title = {Vicinal Counting Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4221-4230} }
What Should Be Equivariant in Self-Supervised Learning: Yuyang Xie,

Jianhong Wen,

Kin Wai Lau,

Yasar Abbas Ur Rehman,

Jiajun Shen; [pdf]
[bibtex]
@InProceedings{Xie_2022_CVPR, author = {Xie, Yuyang and Wen, Jianhong and Lau, Kin Wai and Rehman, Yasar Abbas Ur and Shen, Jiajun}, title = {What Should Be Equivariant in Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4111-4120} }
Zero-Shot Learning Using Multimodal Descriptions: Utkarsh Mall,

Bharath Hariharan,

Kavita Bala; [pdf] [supp]
[bibtex]
@InProceedings{Mall_2022_CVPR, author = {Mall, Utkarsh and Hariharan, Bharath and Bala, Kavita}, title = {Zero-Shot Learning Using Multimodal Descriptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3931-3939} }
Few-Shot Image Classification Along Sparse Graphs: Joseph F. Comer,

Philip L. Jacobson,

Heiko Hoffmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Comer_2022_CVPR, author = {Comer, Joseph F. and Jacobson, Philip L. and Hoffmann, Heiko}, title = {Few-Shot Image Classification Along Sparse Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4187-4195} }
Semantic Pose Verification for Outdoor Visual Localization With Self-Supervised Contrastive Learning: Semih Orhan,

Jose J. Guerrero,

Yalın Baştanlar; [pdf]
[bibtex]
@InProceedings{Orhan_2022_CVPR, author = {Orhan, Semih and Guerrero, Jose J. and Ba\c{s}tanlar, Yal{\i}n}, title = {Semantic Pose Verification for Outdoor Visual Localization With Self-Supervised Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3989-3998} }
Compositional Mixture Representations for Vision and Text: Stephan Alaniz,

Marco Federici,

Zeynep Akata; [pdf]
[bibtex]
@InProceedings{Alaniz_2022_CVPR, author = {Alaniz, Stephan and Federici, Marco and Akata, Zeynep}, title = {Compositional Mixture Representations for Vision and Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4202-4211} }
Self-Supervised Video Representation Learning With Cascade Positive Retrieval: Cheng-En Wu,

Farley Lai,

Yu Hen Hu,

Asim Kadav; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Cheng-En and Lai, Farley and Hu, Yu Hen and Kadav, Asim}, title = {Self-Supervised Video Representation Learning With Cascade Positive Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4070-4079} }
Can Domain Adaptation Make Object Recognition Work for Everyone?: Viraj Prabhu,

Ramprasaath R. Selvaraju,

Judy Hoffman,

Nikhil Naik; [pdf] [arXiv]
[bibtex]
@InProceedings{Prabhu_2022_CVPR, author = {Prabhu, Viraj and Selvaraju, Ramprasaath R. and Hoffman, Judy and Naik, Nikhil}, title = {Can Domain Adaptation Make Object Recognition Work for Everyone?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3981-3988} }
SaR: Self-Adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-Supervised Learning: Zhengfeng Lai,

Chao Wang,

Sen-ching Cheung,

Chen-Nee Chuah; [pdf]
[bibtex]
@InProceedings{Lai_2022_CVPR, author = {Lai, Zhengfeng and Wang, Chao and Cheung, Sen-ching and Chuah, Chen-Nee}, title = {SaR: Self-Adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4091-4100} }