Imbalanced learning for imbalanced recognition and segmentation, including MiSLAS, PaCo, ResLT, RR, ResCom, CeCo, and GPaCo developed by CUHK, Deep Vision Lab.
News
-
2023/05 The paper of GPaCo (Generalized Parametric Contrastive Learning) is accepted by TPAMI 2023.
-
2023/02 The paper of CeCo (Understanding Imbalanced Semantic Segmentation Through Neural Collaps) is accepted by CVPR 2023.
-
2022/07 The code of ResCom has been released!
-
2022/06 The paper of ResLT (ResLT: Residual Learning for Long-Tailed Recognition) is accepted by TPAMI 2022.
-
2022/04 The paper of RR (Region Rebalance for Long-Tailed Semantic Segmentation) is available on arXiv.
-
2022/03 The paper of ResCom (Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition) is available on arXiv.
-
2021/07 The paper of PaCo (Paramateric Contrastive Learning) is accepted by ICCV 2021.
-
2021/03 The paper of MiSLAS (Improving Calibration for Long-Tailed Recognition) is accepted by CVPR 2021.
The repo ./ResCom provides ResCom's trained models, trained log, and code for PyTorch.
The repo ./ResLT provides ResLT's trained models, trained log, and code for PyTorch.
The repo ./Parametric Contrastive Learning provides code and models for PaCo, GPaCo, and RR.
The repo ./MiSLAS provides MiSLAS's trained models, and code for PyTorch.
todo
Please consider citing our papers in your publications if they help your research.
If you have any questions, feel free to contact us through email or Github issues. Thanks!
@ARTICLE{10130611,
author={Cui, Jiequan and Zhong, Zhisheng and Tian, Zhuotao and Liu, Shu and Yu, Bei and Jia, Jiaya},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Generalized Parametric Contrastive Learning},
year={2023},
volume={},
number={},
pages={1-12},
doi={10.1109/TPAMI.2023.3278694}}
@ARTICLE{9774921,
author={Cui, Jiequan and Liu, Shu and Tian, Zhuotao and Zhong, Zhisheng and Jia, Jiaya},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={ResLT: Residual Learning for Long-Tailed Recognition},
year={2023},
volume={45},
number={3},
pages={3695-3706},
doi={10.1109/TPAMI.2022.3174892}
}
@article{cui2022region,
title={Region Rebalance for Long-Tailed Semantic Segmentation},
author={Cui, Jiequan and Yuan, Yuhui and Zhong, Zhisheng and Tian, Zhuotao and Hu, Han and Lin, Stephen and Jia, Jiaya},
journal={arXiv preprint arXiv:2204.01969},
year={2022}
}
@article{zhong2022rescom,
title={Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition},
author={Zhong, Zhisheng and Cui, Jiequan and Lo, Eric and Li, Zeming and Sun, Jian and Jia, Jiaya},
journal={arXiv preprint arXiv:2203.11506},
year={2022}
}
@inproceedings{cui2021parametric,
title={Parametric contrastive learning},
author={Cui, Jiequan and Zhong, Zhisheng and Liu, Shu and Yu, Bei and Jia, Jiaya},
booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
pages={715--724},
year={2021}
}
@inproceedings{zhong2021improving,
title={Improving calibration for long-tailed recognition},
author={Zhong, Zhisheng and Cui, Jiequan and Liu, Shu and Jia, Jiaya},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={16489--16498},
year={2021}
}