Abstract
Self-supervised contrastive learning is popularly used to obtain powerful representation models. However, unlabeled data in the real world naturally exhibits a long-tailed distribution, making the traditional instance-wise contrastive learning unfair to tail samples. Recently, some improvements have been made from the perspective of model, loss, and data to make tail samples highly evaluated during training, but most of them explicitly or implicitly assume that the sample with a large loss is the tail. We argue that due to the lack of hard negatives, tail samples usually occupy a small loss at the initial stage of training, which will make them eliminated at the beginning of training. To address this issue, we propose a simple but effective two-stage learning scheme that decouples traditional contrastive learning to discover and enhance tail samples. Specifically, we identify the sample with a small loss in Stage I while a large loss in Stage II as the tail. With the discovered tail samples, we generate hard negatives for them based on their neighbors, which will balance the distribution of the hard negatives in training and help learn better representation. Additionally, we design the weight inversely proportional or proportional to the loss in each stage to achieve fairer training by reweighting. Extensive experiments on multiple unlabeled long-tailed datasets demonstrate the superiority of our DCL compared with the state-of-the-art methods. The code will be released soon.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: NeurIPS (2019)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597–1607 (2020)
Chen, X., et al.: Area: adaptive reweighting via effective area for long-tailed classification. In: ICCV (2023)
Chen, X., et al.: Imagine by reasoning: a reasoning-based implicit semantic data augmentation for long-tailed classification. In: AAAI, pp. 356–364 (2022)
Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: CVPR, pp. 702–703 (2020)
Cui, J., Zhong, Z., Liu, S., Yu, B., Jia, J.: Parametric contrastive learning. In: ICCV, pp. 715–724 (2021)
Cui, Y., Jia, M., Lin, T.Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: CVPR, pp. 9268–9277 (2019)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)
Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV, pp. 1422–1430 (2015)
Hao, X., Zhang, W., Wu, D., Zhu, F., Li, B.: Dual alignment unsupervised domain adaptation for video-text retrieval. In: CVPR, pp. 18962–18972 (2023)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729–9738 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Jiang, Z., Chen, T., Mortazavi, B.J., Wang, Z.: Self-damaging contrastive learning. In: ICML, pp. 4927–4939 (2021)
Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. In: NeurIPS, pp. 21798–21809 (2020)
Kang, B., Li, Y., Xie, S., Yuan, Z., Feng, J.: Exploring balanced feature spaces for representation learning. In: ICLR (2020)
Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: ICLR (2020)
Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS (2020)
Li, T., et al.: Targeted supervised contrastive learning for long-tailed recognition. In: CVPR, pp. 6918–6928 (2022)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEEICCV, pp. 2980–2988 (2017)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, H., HaoChen, J.Z., Gaidon, A., Ma, T.: Self-supervised learning is more robust to dataset imbalance. In: ICLR (2022)
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: CVPR, pp. 2537–2546 (2019)
Sinha, S., Ohashi, H.: Difficulty-net: learning to predict difficulty for long-tailed recognition. In: WACV, pp. 6433–6442 (2023)
Tian, Y., Henaff, O.J., van den Oord, A.: Divide and contrast: self-supervised learning from uncurated data. In: ICCV, pp. 10063–10074 (2021)
Wang, P., Han, K., Wei, X., Zhang, L., Wang, L.: Contrastive learning based hybrid networks for long-tailed image classification. In: CVPR, pp. 943–952 (2021)
Wu, D., Dai, Q., Liu, J., Li, B., Wang, W.: Deep incremental hashing network for efficient image retrieval. In: CVPR, pp. 9069–9077 (2019)
Xie, S., Girshick, R.B., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 5987–5995 (2017)
Yang, Z., Wu, D., Zhang, W., Li, B., Wang, W.: Handling label uncertainty for camera incremental person re-identification. In: MM (2023)
You, Y., Chen, T., Sui, Y., Chen, T., Wang, Z., Shen, Y.: Graph contrastive learning with augmentations. In: NeurIPS, pp. 5812–5823 (2020)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2018)
Zhang, W., Wu, D., Zhou, Y., Li, B., Wang, W., Meng, D.: Binary neural network hashing for image retrieval. In: SIGIR, pp. 317–326 (2021)
Zhao, S., Wu, D., Zhang, W., Zhou, Y., Li, B., Wang, W.: Asymmetric deep hashing for efficient hash code compression. In: MM, pp. 763–771 (2020)
Zhao, S., Wu, D., Zhou, Y., Li, B., Wang, W.: Rescuing deep hashing from dead bits problem. In: IJCAI, pp. 1338–1344 (2021)
Zhou, Z., Yao, J., Wang, Y.F., Han, B., Zhang, Y.: Contrastive learning with boosted memorization. In: ICML, pp. 27367–27377 (2022)
Zhu, J., Wang, Z., Chen, J., Chen, Y.P., Jiang, Y.: Balanced contrastive learning for long-tailed visual recognition. In: CVPR, pp. 6898–6907 (2022)
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grants 62006221, 62106258, 62006242, 62202459 and 61925602, the National Key R&D Program of China under Grant 2022YFB31 03500, the Grant No. XDC02050200, the China Postdoctoral Science Foundation under Grant 2022M713348 and 2022TQ0363, and Young Elite Scientists Sponsorship Program by BAST (No. BYESS2023304).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, X. et al. (2024). Decoupled Contrastive Learning for Long-Tailed Distribution. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14433. Springer, Singapore. https://doi.org/10.1007/978-981-99-8546-3_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-8546-3_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8545-6
Online ISBN: 978-981-99-8546-3
eBook Packages: Computer ScienceComputer Science (R0)