Abstract
Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. This problem is often aggravated by discrepancies between labeled and unlabeled class distributions, leading to biased pseudo-labels, neglect of rare classes, and poorly calibrated probabilities. To address these issues, we introduce Flexible Distribution Alignment (FlexDA), a novel adaptive logit-adjusted loss framework designed to dynamically estimate and align predictions with the actual distribution of unlabeled data and achieve a balanced classifier by the end of training. FlexDA is further enhanced by a distillation-based consistency loss, promoting fair data usage across classes and effectively leveraging underconfident samples. This method, encapsulated in ADELLO (Align and Distill Everything All at Once), proves robust against label shift, significantly improves model calibration in LTSSL contexts, and surpasses previous state-of-of-art approaches across multiple benchmarks, including CIFAR100-LT, STL10-LT, and ImageNet127, addressing class imbalance challenges in semi-supervised learning. Our code is available at https://github.com/emasa/ADELLO-LTSSL.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aimar, E.S., Jonnarth, A., Felsberg, M., Kuhlmann, M.: Balanced product of calibrated experts for long-tailed recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19967–19977 (2023)
Arazo, E., Ortego, D., Albert, P., O’Connor, N.E., McGuinness, K.: Pseudo-labeling and confirmation bias in deep semi-supervised learning. In: International Joint Conference on Neural Networks (IJCNN), IEEE (2020)
Berthelot, D., et al.: RemixMatch: semi-supervised learning with distribution matching and augmentation anchoring. In: 8th International Conference on Learning Representations (2020)
Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: MixMatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems (2019)
Berthelot, D., Roelofs, R., Sohn, K., Carlini, N., Kurakin, A.: AdaMatch: a unified approach to semi-supervised learning and domain adaptation (2021)
Brodersen, K.H., Ong, C.S., Stephan, K.E., Buhmann, J.M.: The balanced accuracy and its posterior distribution. In: 2010 20th International Conference on Pattern Recognition, pp. 3121–3124. IEEE (2010)
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 (2019)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9912–9924 (2020)
Chan, P.K., Stolfo, S.J.: Learning with non-uniform class and cost distributions: effects and a distributed multi-classifier approach. In: In Workshop Notes KDD-98 Workshop on Distributed Data Mining (1998)
Chapelle, O., Schölkopf, B., Zien, A.: Semi-supervised learning (Chapelle, O. et al., eds.; 2006). IEEE Trans. Neural Netw. 20(3) (2009)
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, H., et al.: SoftMatch: addressing the quantity-quality tradeoff in semi-supervised learning. In: Eleventh International Conference on Learning Representations. OpenReview. net (2023)
Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (2011)
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 (2019)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)
Fan, Y., Dai, D., Schiele, B.: CoSSL: co-learning of representation and classifier for imbalanced semi-supervised learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)
Friedman, M.: The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J. Am. Stat. Assoc. 32, 675–701 (1937). https://api.semanticscholar.org/CorpusID:120581754
Friedman, M.: A comparison of alternative tests of significance for the problem of \$m\$ rankings. Ann. Math. Stat. 11, 86–92 (1940). https://api.semanticscholar.org/CorpusID:121778036
Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: Advances in Neural Information Processing Systems (2005)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, pp. 1321–1330. PMLR (2017)
Guo, L.Z., Li, Y.F.: Class-imbalanced semi-supervised learning with adaptive thresholding. In: International Conference on Machine Learning, pp. 8082–8094. PMLR (2022)
He, Y.Y., Wu, J., Wei, X.S.: Distilling virtual examples for long-tailed recognition. 2021 IEEE/CVF International Conference on Computer Vision (ICCV) (2021). https://doi.org/10.1109/iccv48922.2021.00030, http://dx.doi.org/10.1109/ICCV48922.2021.00030
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
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 (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 (2016)
Huh, M., Agrawal, P., Efros, A.A.: What makes ImageNet good for transfer learning? arXiv preprint arXiv:1608.08614 (2016)
Hyun, M., Jeong, J., Kwak, N.: Class-imbalanced semi-supervised learning. arXiv preprint arXiv:2002.06815 (2020)
Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: International Conference on Learning Representations (2020)
Kim, J., Hur, Y., Park, S., Yang, E., Hwang, S., Shin, J.: Distribution aligning refinery of pseudo-label for imbalanced semi-supervised learning. In: Advances in Neural Information Processing Systems (2020)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: International Conference on Learning Representations (2015)
Krause, A., Perona, P., Gomes, R.: Discriminative clustering by regularized information maximization. In: Advances in Neural Information Processing Systems, vol. 23 (2010)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report (2009)
Kubat, M., Matwin, S., et al.: Addressing the curse of imbalanced training sets: one-sided selection. In: ICML, vol. 97, p. 179 (1997)
Kuo, C.-W., Ma, C.-Y., Huang, J.-B., Kira, Z.: FeatMatch: feature-based augmentation for semi-supervised learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 479–495. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58523-5_28
Lai, Z., Wang, C., Gunawan, H., Cheung, S.C.S., Chuah, C.N.: Smoothed adaptive weighting for imbalanced semi-supervised learning: improve reliability against unknown distribution data. In: International Conference on Machine Learning, pp. 11828–11843. PMLR (2022)
Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: 5th International Conference on Learning Representations (2017)
Lazarow, J., Sohn, K., Lee, C.Y., Li, C.L., Zhang, Z., Pfister, T.: Unifying distribution alignment as a loss for imbalanced semi-supervised learning. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 5644–5653 (2023)
Lee, D.H.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML (2013)
Lee, H., Shin, S., Kim, H.: Abc: Auxiliary balanced classifier for class-imbalanced semi-supervised learning. In: Advances in Neural Information Processing Systems, vol. 34, pp. 7082–7094 (2021)
Li, J., Tan, Z., Wan, J., Lei, Z., Guo, G.: Nested collaborative learning for long-tailed visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6949–6958 (2022)
Li, Z., Hoiem, D.: Improving confidence estimates for unfamiliar examples. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2686–2695 (2020)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017). https://doi.org/10.1109/iccv.2017.324, http://dx.doi.org/10.1109/ICCV.2017.324
Lipton, Z., Wang, Y.X., Smola, A.: Detecting and correcting for label shift with black box predictors. In: International Conference on Machine Learning, pp. 3122–3130. PMLR (2018)
Loh, C., et al.: On the importance of calibration in semi-supervised learning. arXiv preprint arXiv:2210.04783 (2022)
Lucas, T., Weinzaepfel, P., Rogez, G.: Barely-supervised learning: semi-supervised learning with very few labeled images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 2, pp. 1881–1889 (2022). https://doi.org/10.1609/aaai.v36i2.20082
Ma, C., Elezi, I., Deng, J., Dong, W., Xu, C.: Three heads are better than one: Complementary experts for long-tailed semi-supervised learning. arXiv preprint arXiv:2312.15702 (2023)
McLachlan, G.J.: Iterative reclassification procedure for constructing an asymptotically optimal rule of allocation in discriminant analysis. J. Am. Stat. Assoc. 70(350), 365–369 (1975)
Menon, A.K., Jayasumana, S., Rawat, A.S., Jain, H., Veit, A., Kumar, S.: Long-tail learning via logit adjustment. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=37nvvqkCo5
Miyato, T., Maeda, S.I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE trans. Pattern Anal. Mach. Intell. 41(8) (2018)
Morik, K., Brockhausen, P., Joachims, T.: Combining statistical learning with a knowledge-based approach: a case study in intensive care monitoring. Technical report (1999)
Oh, Y., Kim, D.J., Kweon, I.S.: DASO: distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022). https://doi.org/10.1109/cvpr52688.2022.00956, http://dx.doi.org/10.1109/CVPR52688.2022.00956
Park, S., Hong, Y., Heo, B., Yun, S., Choi, J.Y.: The majority can help the minority: context-rich minority oversampling for long-tailed classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6887–6896 (2022)
Powers, D.M.: Applications and explanations of Zipf’s law. In: New Methods in Language Processing and Computational Natural Language Learning (1998)
Reiter, R.: On Closed World Data Bases, pp. 300–310. Morgan Kaufmann Publishers Inc., San Francisco (1987)
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, 4175–4186 (2020)
Sajjadi, M., Javanmardi, M., Tasdizen, T.: Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In: Advances in Neural Information Processing Systems (2016)
Scudder, H.: Probability of error of some adaptive pattern-recognition machines. IEEE Trans. Inf. Theory 11, 363–371 (1965)
Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems (2020)
Tan, J., et al.: Equalization loss for long-tailed object recognition. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https://doi.org/10.1109/cvpr42600.2020.01168, http://dx.doi.org/10.1109/cvpr42600.2020.01168
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems (2017)
Van Horn, G., Perona, P.: The devil is in the tails: fine-grained classification in the wild. arXiv preprint arXiv:1709.01450 (2017)
Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: International Conference on Machine Learning, pp. 6438–6447. PMLR (2019)
Wallace, B.C., Small, K., Brodley, C.E., Trikalinos, T.A.: Class imbalance, redux. In: 2011 IEEE 11th International Conference on Data Mining, pp. 754–763. IEEE (2011)
Wang, X., Wu, Z., Lian, L., Yu, S.X.: Debiased learning from naturally imbalanced pseudo-labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14647–14657 (2022)
Wang, Y., et al.: USB: a unified semi-supervised learning benchmark for classification (2022)
Wang, Y., et al.: FreeMatch: self-adaptive thresholding for semi-supervised learning. arXiv preprint arXiv:2205.07246 (2022)
Wang, Y.X., Ramanan, D., Hebert, M.: Learning to model the tail. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper_files/paper/2017/file/147ebe637038ca50a1265abac8dea181-Paper.pdf
Wei, C., Sohn, K., Mellina, C., Yuille, A., Yang, F.: CReST: a class-rebalancing self-training framework for imbalanced semi-supervised learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)
Wei, T., Gan, K.: Towards realistic long-tailed semi-supervised learning: consistency is all you need. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3469–3478 (2023)
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, Part V. LNCS, vol. 12350, pp. 247–263. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_15
Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation for consistency training. In: Advances in Neural Information Processing Systems (2019)
Xie, Y., Manski, C.F.: The logit model and response-based samples. Sociol. Methods Res. 17(3), 283–302 (1989)
Xu, Y., et al.: Dash: semi-supervised learning with dynamic thresholding. In: International Conference on Machine Learning, pp. 11525–11536. PMLR (2021)
Xu, Z., Chai, Z., Yuan, C.: Towards calibrated model for long-tailed visual recognition from prior perspective (2021)
Xu, Z., Chai, Z., Yuan, C.: Towards calibrated model for long-tailed visual recognition from prior perspective. In: Advances in Neural Information Processing Systems, vol. 34, pp. 7139–7152 (2021)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6023–6032 (2019)
Zagoruyko, S., Komodakis, N.: Wide residual networks (2017)
Zhang, B., et al.: FlexMatch: boosting semi-supervised learning with curriculum pseudo labeling. In: Advances in Neural Information Processing Systems, vol. 34 (2021)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: 6th International Conference on Learning Representations, ICLR (2018)
Zhang, Y., Hooi, B., Hong, L., Feng, J.: Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition. In: Advances in Neural Information Processing Systems, vol. 35, pp. 34077–34090 (2022)
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)
Zhu, X., Anguelov, D., Ramanan, D.: Capturing long-tail distributions of object subcategories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
Acknowledgements
This work was supported by the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP), funded by the Knut and Alice Wallenberg Foundation. The computational resources were provided by the National Academic Infrastructure for Supercomputing in Sweden (NAISS), partially funded by the Swedish Research Council through grant agreement no. 2022-06725, and by the Berzelius resource, provided by the Knut and Alice Wallenberg Foundation at the National Supercomputer Centre.
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
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sanchez Aimar, E., Helgesen, N., Xu, Y., Kuhlmann, M., Felsberg, M. (2025). Flexible Distribution Alignment: Towards Long-Tailed Semi-supervised Learning with Proper Calibration. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15112. Springer, Cham. https://doi.org/10.1007/978-3-031-72949-2_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-72949-2_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72948-5
Online ISBN: 978-3-031-72949-2
eBook Packages: Computer ScienceComputer Science (R0)