Abstract
Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little attention has been given to how to quantify the dominance severity of head classes in the representation space. Motivated by this, we generalize the cosine-based classifiers to a von Mises-Fisher (vMF) mixture model, denoted as vMF classifier, which enables to quantitatively measure representation quality upon the hyper-sphere space via calculating distribution overlap coefficient. To our knowledge, this is the first work to measure representation quality of classifiers and features from the perspective of distribution overlap coefficient. On top of it, we formulate the inter-class discrepancy and class-feature consistency loss terms to alleviate the interference among the classifier weights and align features with classifier weights. Furthermore, a novel post-training calibration algorithm is devised to zero-costly boost the performance via inter-class overlap coefficients. Our method outperforms previous work with a large margin and achieves state-of-the-art performance on long-tailed image classification, semantic segmentation, and instance segmentation tasks (e.g., we achieve 55.0% overall accuracy with ResNetXt-50 in ImageNet-LT). Our code is available at https://github.com/VipaiLab/vMF_OP.
H. Wang and S. Fu—These authors contributed equally.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cai, Z., Vasconcelos, N.: Cascade r-cnn: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483–1498 (2019)
Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. Adv. Neural Inf. Process. Syst. 32 (2019)
Chen, K., et al.: Mmdetection: open mmlab detection toolbox and benchmark. ar**v preprint ar**v:1906.07155 (2019)
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818 (2018)
Cui, J., Zhong, Z., Liu, S., Yu, B., Jia, J.: Parametric contrastive learning (2021)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Dhaker, H., Ngom, P., Mbodj, M.: Overlap coefficients based on kullback-leibler divergence: exponential populations case. Int. J. Appl. Math. Res. 6(4) (2017)
Diethe, T.: A note on the kullback-leibler divergence for the von mises-fisher distribution. ar**v preprint ar**v:1502.07104 (2015)
Gupta, A., Dollar, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5356–5364 (2019)
Hasnat, M., Bohné, J., Milgram, J., Gentric, S., Chen, L., et al.: von mises-fisher mixture model-based deep learning: application to face verification. ar**v preprint ar**v:1706.04264 (2017)
He, K., Fan, H., Wu, Y., **e, 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., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
Hong, Y., Han, S., Choi, K., Seo, S., Kim, B., Chang, B.: Disentangling label distribution for long-tailed visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6626–6636 (2021)
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)
Jupp, P.E., Mardia, K.V.: Maximum likelihood estimators for the matrix von mises-fisher and bingham distributions. Ann. Stat. 7(3), 599–606 (1979)
Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition (2019)
Kang, B., Li, Y., **e, S., Yuan, Z., Feng, J.: Exploring balanced feature spaces for representation learning. In: International Conference on Learning Representations (2021)
Kent, J.: Some probabilistic properties of bessel functions. Ann. Probabil., 760–770 (1978)
Kobayashi, T.: t-vmf similarity for regularizing intra-class feature distribution. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6612–6621 (2021)
Li, S., Xu, J., Xu, X., Shen, P., Li, S., Hooi, B.: Spherical confidence learning for face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15629–15637 (2021)
Li, T., et al.: Targeted supervised contrastive learning for long-tailed recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6918–6928 (2022)
Li, Y., et al.: Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10991–11000 (2020)
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, B., Li, H., Kang, H., Hua, G., Vasconcelos, N.: Gistnet: a geometric structure transfer network for long-tailed recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8209–8218 (2021)
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
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)
Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. ar**v preprint ar**v:1608.03983 (2016)
Mash’al, M., Hosseini, R.: K-means++ for mixtures of von mises-fisher distributions. In: 2015 7th Conference on Information and Knowledge Technology (IKT), pp. 1–6. IEEE (2015)
Nicholls, E., Stark, A.: Bayes’ theorem. Med. J. Aust. 2(26), 1335–1339 (1971)
Papadopoulos, C.I.: On the Kullback-Leibler information measure and statistical inference. Wayne State University (1971)
Peng, Z., Huang, W., Guo, Z., Zhang, X., Jiao, J., Ye, Q.: Long-tailed distribution adaptation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3275–3282 (2021)
Ren, J., Yu, C., Ma, X., Zhao, H., Yi, S., et al.: Balanced meta-softmax for long-tailed visual recognition. Adv. Neural Inf. Process. Syst. 33, 4175–4186 (2020)
Romanazzi, M.: Discriminant analysis with high dimensional von mises-fisher distributions. In: 8th Annual International Conference on Statistics, pp. 1–16. Athens Institute for Education and Research (2014)
Samuel, D., Chechik, G.: Distributional robustness loss for long-tail learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)
Tan, J., Lu, X., Zhang, G., Yin, C., Li, Q.: Equalization loss v2: a new gradient balance approach for long-tailed object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1685–1694 (2021)
Tan, J., et al.: Equalization loss for long-tailed object recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11662–11671 (2020)
Tang, K., Huang, J., Zhang, H.: Long-tailed classification by kee** the good and removing the bad momentum causal effect. In: NeurIPS (2020)
Tang, K., Huang, J., Zhang, H.: Long-tailed classification by kee** the good and removing the bad momentum causal effect. Adv. Neural Inf. Process. Syst. 33, 1513–1524 (2020)
Van Horn, G., et al.: The inaturalist species classification and detection dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8769–8778 (2018)
Wang, J., et al.: Seesaw loss for long-tailed instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (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.: Long-tailed recognition by routing diverse distribution-aware experts. In: International Conference on Learning Representations (2021)
Weng, Z., Ogut, M.G., Limonchik, S., Yeung, S.: Unsupervised discovery of the long-tail in instance segmentation using hierarchical self-supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2603–2612 (2021)
Wu, T., Liu, Z., Huang, Q., Wang, Y., Lin, D.: Adversarial robustness under long-tailed distribution (2021)
Wu, T.Y., Morgado, P., Wang, P., Ho, C.H., Vasconcelos, N.: Solving long-tailed recognition with deep realistic taxonomic classifier
**e, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. ar**v preprint ar**v:1611.05431 (2016)
Yang, Y., Xu, Z.: Rethinking the value of labels for improving class-imbalanced learning. Adv. Neural Inf. Process. Syst. 33, 19290–19301 (2020)
Ye, H.J., Chen, H.Y., Zhan, D.C., Chao, W.L.: Identifying and compensating for feature deviation in imbalanced deep learning (2020)
Yuan, Y., Wang, J.: Ocnet: object context network for scene parsing (2018)
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, X., Fang, Z., Wen, Y., Li, Z., Qiao, Y.: Range loss for deep face recognition with long-tailed training data. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5409–5418 (2017)
Zhang, Y., Hooi, B., Hong, L., Feng, J.: Test-agnostic long-tailed recognition by test-time aggregating diverse experts with self-supervision. ar**v preprint ar**v:2107.09249 (2021)
Zhang, Y., Kang, B., Hooi, B., Yan, S., Feng, J.: Deep long-tailed learning: a survey. ar**v preprint ar**v:2110.04596 (2021)
Zhong, Z., Cui, J., Liu, S., Jia, J.: Improving calibration for long-tailed recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16489–16498 (2021)
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633–641 (2017)
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)
Zhu, B., Niu, Y., Hua, X.S., Zhang, H.: Cross-domain empirical risk minimization for unbiased long-tailed classification. In: AAAI Conference on Artificial Intelligence (2022)
Zhu, L., Yang, Y.: Inflated episodic memory with region self-attention for long-tailed visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4344–4353 (2020)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (U21B2004), the Zhejiang Provincial key RD Program of China (2021C01119) , and the Zhejiang University-Angelalign Inc. R & D Center for Intelligent Healthcare.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, H., Fu, S., He, X., Fang, H., Liu, Z., Hu, H. (2022). Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13684. Springer, Cham. https://doi.org/10.1007/978-3-031-20053-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-20053-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20052-6
Online ISBN: 978-3-031-20053-3
eBook Packages: Computer ScienceComputer Science (R0)