Abstract
Training deep neural networks with empirical risk minimization (ERM) often captures dataset biases, hindering generalization to new or unseen data. Previous solutions either require prior knowledge of biases or utilize training intentionally biased models as auxiliaries; however, they still suffer from multiple biases. To address this, we introduce Adaptive Bias Discovery (ABD), a novel learning framework designed to mitigate the impact of multiple unknown biases. ABD trains an auxiliary model to be adapted to biases based on the debiased parameters from the debiasing phase, allowing it to navigate through multiple biases. Then, samples are reweighted based on the discovered biases to update debiased parameters. Extensive evaluations of synthetic experiments and real-world datasets demonstrate that ABD consistently outperforms existing methods, particularly in real-world applications where multiple unknown biases are prevalent.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)
Arpit, D., Jastrzębski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M.S., Maharaj, T., Fischer, A., Courville, A., Bengio, Y., et al.: A closer look at memorization in deep networks. In: International Conference on Machine Learning. pp. 233–242. PMLR (2017)
Bandi, P., Geessink, O., Manson, Q., Van Dijk, M., Balkenhol, M., Hermsen, M., Bejnordi, B.E., Lee, B., Paeng, K., Zhong, A., et al.: From detection of individual metastases to classification of lymph node status at the patient level: the camelyon17 challenge. IEEE Trans. Med. Imaging 38(2), 550–560 (2018)
Bao, Y., Chang, S., Barzilay, R.: Predict then interpolate: A simple algorithm to learn stable classifiers. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 640–650. PMLR (18–24 Jul 2021), https://proceedings.mlr.press/v139/bao21a.html
Beery, S., Van Horn, G., Perona, P.: Recognition in terra incognita. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 456–473 (2018)
Belinkov, Y., Poliak, A., Shieber, S.M., Van Durme, B., Rush, A.M.: Don’t take the premise for granted: Mitigating artifacts in natural language inference. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 877–891 (2019)
Belinkov, Y., Poliak, A., Shieber, S.M., Van Durme, B., Rush, A.M.: On adversarial removal of hypothesis-only bias in natural language inference. In: Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (* SEM 2019). pp. 256–262 (2019)
Ben-Tal, A., Den Hertog, D., De Waegenaere, A., Melenberg, B., Rennen, G.: Robust solutions of optimization problems affected by uncertain probabilities. Manage. Sci. 59(2), 341–357 (2013)
Borkan, D., Dixon, L., Sorensen, J., Thain, N., Vasserman, L.: Nuanced metrics for measuring unintended bias with real data for text classification. In: Companion proceedings of the 2019 world wide web conference. pp. 491–500 (2019)
Christie, G., Fendley, N., Wilson, J., Mukherjee, R.: Functional map of the world. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6172–6180 (2018)
Clark, C., Yatskar, M., Zettlemoyer, L.: Don’t take the easy way out: Ensemble based methods for avoiding known dataset biases. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). pp. 4069–4082 (2019)
Duchi, J.C., Glynn, P.W., Namkoong, H.: Statistics of robust optimization: A generalized empirical likelihood approach. Math. Oper. Res. 46(3), 946–969 (2021)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning. pp. 1126–1135. PMLR (2017)
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)
Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S., Smith, N.A.: Annotation artifacts in natural language inference data. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). pp. 107–112 (2018)
de Haan, P., Jayaraman, D., Levine, S.: Causal confusion in imitation learning. In: Advances in Neural Information Processing Systems. pp. 11698–11709 (2019)
He, H., Zha, S., Wang, H.: Unlearn dataset bias in natural language inference by fitting the residual. In: Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019). pp. 132–142 (2019)
Hu, W., Niu, G., Sato, I., Sugiyama, M.: Does distributionally robust supervised learning give robust classifiers? In: International Conference on Machine Learning. pp. 2029–2037. PMLR (2018)
Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., Madry, A.: Adversarial examples are not bugs, they are features. In: Advances in Neural Information Processing Systems. pp. 125–136 (2019)
Kim, N., Hwang, S., Ahn, S., Park, J., Kwak, S.: Learning debiased classifier with biased committee. Adv. Neural. Inf. Process. Syst. 35, 18403–18415 (2022)
Koh, P.W., Sagawa, S., Xie, S.M., Zhang, M., Balsubramani, A., Hu, W., Yasunaga, M., Phillips, R.L., Gao, I., Lee, T., et al.: Wilds: A benchmark of in-the-wild distribution shifts. In: International Conference on Machine Learning. pp. 5637–5664. PMLR (2021)
Liang, W., Zou, J.: Metashift: A dataset of datasets for evaluating contextual distribution shifts and training conflicts. In: International Conference on Learning Representations (2022), https://openreview.net/forum?id=MTex8qKavoS
Liu, E.Z., Haghgoo, B., Chen, A.S., Raghunathan, A., Koh, P.W., Sagawa, S., Liang, P., Finn, C.: Just train twice: Improving group robustness without training group information. In: International Conference on Machine Learning. pp. 6781–6792. PMLR (2021)
Mahabadi, R.K., Belinkov, Y., Henderson, J.: End-to-end bias mitigation by modelling biases in corpora. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. pp. 8706–8716 (2020)
McCoy, T., Pavlick, E., Linzen, T.: Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 3428–3448 (2019)
Nam, J., Cha, H., Ahn, S., Lee, J., Shin, J.: Learning from failure: De-biasing classifier from biased classifier. Adv. Neural. Inf. Process. Syst. 33, 20673–20684 (2020)
Piratla, V., Netrapalli, P., Sarawagi, S.: Focus on the common good: Group distributional robustness follows. In: International Conference on Learning Representations (2022), https://openreview.net/forum?id=irARV_2VFs4
Poliak, A., Naradowsky, J., Haldar, A., Rudinger, R., Van Durme, B.: Hypothesis only baselines in natural language inference. In: Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics. pp. 180–191 (2018)
Sagawa*, S., Koh*, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks. In: International Conference on Learning Representations (2020), https://openreview.net/forum?id=ryxGuJrFvS
Sanh, V., Wolf, T., Belinkov, Y., Rush, A.M.: Learning from others’ mistakes: Avoiding dataset biases without modeling them. In: International Conference on Learning Representations (2021), https://openreview.net/forum?id=Hf3qXoiNkR
Schuster, T., Shah, D., Yeo, Y.J.S., Ortiz, D.R.F., Santus, E., Barzilay, R.: Towards debiasing fact verification models. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). pp. 3419–3425 (2019)
Scimeca, L., Oh, S.J., Chun, S., Poli, M., Yun, S.: Which shortcut cues will DNNs choose? a study from the parameter-space perspective. In: International Conference on Learning Representations (2022), https://openreview.net/forum?id=qRDQi3ocgR3
Sun, B., Saenko, K.: Deep coral: Correlation alignment for deep domain adaptation. In: Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III 14. pp. 443–450. Springer (2016)
Utama, P.A., Moosavi, N.S., Gurevych, I.: Towards debiasing nlu models from unknown biases. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 7597–7610 (2020)
Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). pp. 1112–1122 (2018)
Yao, H., Wang, Y., Li, S., Zhang, L., Liang, W., Zou, J., Finn, C.: Improving out-of-distribution robustness via selective augmentation. In: International Conference on Machine Learning. pp. 25407–25437. PMLR (2022)
Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: HellaSwag: Can a machine really finish your sentence? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 4791–4800. Association for Computational Linguistics, Florence, Italy (Jul 2019). https://doi.org/10.18653/v1/P19-1472, https://aclanthology.org/P19-1472
Acknowledgements
This research was supported by the Core Research Institute Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2021R1A6A1A03043144) and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. RS-2023-00241123).
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 Singapore Pte Ltd.
About this paper
Cite this paper
Bae, JH., Lee, M., Jung, H. (2025). Adaptive Bias Discovery for Learning Debiased Classifier. In: Cho, M., Laptev, I., Tran, D., Yao, A., Zha, H. (eds) Computer Vision – ACCV 2024. ACCV 2024. Lecture Notes in Computer Science, vol 15479. Springer, Singapore. https://doi.org/10.1007/978-981-96-0966-6_3
Download citation
DOI: https://doi.org/10.1007/978-981-96-0966-6_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-96-0965-9
Online ISBN: 978-981-96-0966-6
eBook Packages: Computer ScienceComputer Science (R0)