Abstract
Visual recognition methods assume models will be evaluated on the same class distribution as training data, but real-world data is often heavily class-imbalanced. To address this, the essential idea is to provide discriminative fitting abilities for classes with different sample sizes, i.e., the model achieves better generalization on less frequent classes, while maintaining high classification ability on the recurring classes. In this work, we propose to unify representation learning and classification learning with robust margin adjustment, which enforces a suitable margin in logit space and regularizes the distribution of embeddings. This procedure reduces representation bias in the feature space and reduces classification bias in the logit space at the same time. We further augment the under-represented tail classes on the feature level via re-balanced sampling from the robust prototype, calibrated with the knowledge from well-represented head classes and adaptive embedding uncertainty estimation. We conduct extensive experiments on a common long-tailed benchmark CIFAR100-LT. Experimental results demonstrate the advantage of the proposed AMDRG for the long-tailed recognition problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cao, D., Zhu, X., Huang, X., Guo, J., Lei, Z.: Domain balancing: face recognition on long-tailed domains. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5671–5679 (2020)
Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)
Chu, P., Bian, X., Liu, S., Ling, H.: Feature space augmentation for long-tailed data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 694–710. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58526-6_41
Cui, J., Zhong, Z., Liu, S., Yu, B., Jia, J.: Parametric contrastive learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 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: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9268–9277 (2019)
Deng, Z., Liu, H., Wang, Y., Wang, C., Yu, Z., Sun, X.: PML: progressive margin loss for long-tailed age classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10503–10512 (2021)
Feng, C., Zhong, Y., Huang, W.: Exploring classification equilibrium in long-tailed object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3417–3426 (2021)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5375–5384 (2016)
Japkowicz, N., Stephen, S.: The class imbalance problem: a systematic study. Intell. Data Anal. 6(5), 429–449 (2002)
Jitkrittum, W., Menon, A.K., Rawat, A.S., Kumar, S.: ELM: embedding and logit margins for long-tail learning. arXiv preprint arXiv:2204.13208 (2022)
Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019)
Khan, S., Hayat, M., Zamir, S.W., Shen, J., Shao, L.: Striking the right balance with uncertainty. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 103–112 (2019)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Liu, X.Y., Wu, J., Zhou, Z.H.: Exploratory undersampling for class-imbalance learning. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 39(2), 539–550 (2008)
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2537–2546 (2019)
Menon, A.K., Jayasumana, S., Rawat, A.S., Jain, H., Veit, A., Kumar, S.: Long-tail learning via logit adjustment. arXiv preprint arXiv:2007.07314 (2020)
Oh, Y., Kim, D.J., Kweon, I.S.: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning. arXiv preprint arXiv:2106.05682 (2021)
Ren, J., Yu, C., Ma, X., Zhao, H., Yi, S., et al.: Balanced meta-softmax for long-tailed visual recognition. In: Advances in Neural Information Processing Systems, vol. 33, pp. 4175–4186 (2020)
Samuel, D., Atzmon, Y., Chechik, G.: From generalized zero-shot learning to long-tail with class descriptors. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 286–295 (2021)
Samuel, D., Chechik, G.: Distributional robustness loss for long-tail learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9495–9504 (2021)
Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926–930 (2018)
Wang, J., Lukasiewicz, T., Hu, X., Cai, J., Xu, Z.: RSG: a simple but effective module for learning imbalanced datasets. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3784–3793 (2021)
Wang, P., Han, K., Wei, X.S., Zhang, L., Wang, L.: Contrastive learning based hybrid networks for long-tailed image classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 943–952 (2021)
Wang, X., Lian, L., Miao, Z., Liu, Z., Yu, S.X.: Long-tailed recognition by routing diverse distribution-aware experts. arXiv preprint arXiv:2010.01809 (2020)
Wang, Y.X., Ramanan, D., Hebert, M.: Learning to model the tail. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wu, T., Liu, Z., Huang, Q., Wang, Y., Lin, D.: Adversarial robustness under long-tailed distribution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8659–8668 (2021)
Xiang, L., Ding, G., Han, J.: Learning from multiple experts: self-paced knowledge distillation for long-tailed classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 247–263. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_15
Ye, H.J., Chen, H.Y., Zhan, D.C., Chao, W.L.: Identifying and compensating for feature deviation in imbalanced deep learning. arXiv preprint arXiv:2001.01385 (2020)
Zhang, S., Li, Z., Yan, S., He, X., Sun, J.: Distribution alignment: a unified framework for long-tail visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2361–2370 (2021)
Zhang, Y., Hooi, B., Hong, L., Feng, J.: Test-agnostic long-tailed recognition by test-time aggregating diverse experts with self-supervision. arXiv preprint arXiv:2107.09249 (2021)
Zhang, Y., et al.: Online adaptive asymmetric active learning for budgeted imbalanced data. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2768–2777 (2018)
Zhang, Y., et al.: Online adaptive asymmetric active learning with limited budgets. IEEE Trans. Knowl. Data Eng. 33(6), 2680–2692 (2019)
Zhang, Z., Xiang, X.: Long-tailed classification with gradual balanced loss and adaptive feature generation. arXiv preprint arXiv:2203.00452 (2022)
Zhang, Z., Pfister, T.: Learning fast sample re-weighting without reward data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 725–734 (2021)
Zhao, P., Zhang, Y., Wu, M., Hoi, S.C., Tan, M., Huang, J.: Adaptive cost-sensitive online classification. IEEE Trans. Knowl. Data Eng. 31(2), 214–228 (2018)
Zhou, B., Cui, Q., Wei, X.S., Chen, Z.M.: BBN: bilateral-branch network with cumulative learning for long-tailed visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9719–9728 (2020)
Acknowledgements
This work was partly supported by NSFC (U19B2035) and Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Su, Y., Chen, B., Feng, Z., Yan, J. (2023). Adaptive Embedding and Distribution Re-margin for Long-Tail Recognition. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14261. Springer, Cham. https://doi.org/10.1007/978-3-031-44198-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-44198-1_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44197-4
Online ISBN: 978-3-031-44198-1
eBook Packages: Computer ScienceComputer Science (R0)