Abstract
Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually simple yet efficient training block, termed as Attentive Feature Mixup (AFM), which allows paying more attention to clean samples and less to mislabeled ones via sample interactions in small groups. Specifically, this plug-and-play AFM first leverages a group-to-attend module to construct groups and assign attention weights for group-wise samples, and then uses a mixup module with the attention weights to interpolate massive noisy-suppressed samples. The AFM has several appealing benefits for noise-robust deep learning. (i) It does not rely on any assumptions and extra clean subset. (ii) With massive interpolations, the ratio of useless samples is reduced dramatically compared to the original noisy ratio. (iii) It jointly optimizes the interpolation weights with classifiers, suppressing the influence of mislabeled data via low attention weights. (iv) It partially inherits the vicinal risk minimization of mixup to alleviate over-fitting while improves it by sampling fewer feature-target vectors around mislabeled data from the mixup vicinal distribution. Extensive experiments demonstrate that AFM yields state-of-the-art results on two challenging real-world noisy datasets: Food101N and Clothing1M.
X. Peng, K. Wang and Z. Zeng—Equally-contributed first authors.
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
Arazo, E., Ortego, D., Albert, P., O’Connor, N.E., McGuinness, K.: Unsupervised label noise modeling and loss correction (2019)
Arpit, D., et al.: A closer look at memorization in deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 233–242. JMLR. org (2017)
Barandela, R., Gasca, E.: Decontamination of training samples for supervised pattern recognition methods. In: Ferri, F.J., Iñesta, J.M., Amin, A., Pudil, P. (eds.) SSPR /SPR 2000. LNCS, vol. 1876, pp. 621–630. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-44522-6_64
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML, pp. 41–48. ACM (2009)
Brodley, C.E., Friedl, M.A.: Identifying mislabeled training data. J. Artif. Intell. Res. 11, 131–167 (1999)
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. IEEE (2009)
Frénay, B., Verleysen, M.: Classification in the presence of label noise: a survey. TNNLS 25(5), 845–869 (2014)
Gong, Y., Ke, Q., Isard, M., Lazebnik, S.: A multi-view embedding space for modeling internet images, tags, and their semantics. IJCV 106(2), 210–233 (2014). https://doi.org/10.1007/s11263-013-0658-4
Guo, H., Mao, Y., Zhang, R.: Mixup as locally linear out-of-manifold regularization. In: AAAI, vol. 33, pp. 3714–3722 (2019)
Guo, S., et al.: CurriculumNet: weakly supervised learning from large-scale web images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 139–154. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_9
Han, J., Luo, P., Wang, X.: Deep self-learning from noisy labels. In: ICCV (2019)
Jiang, L., Zhou, Z., Leung, T., Li, L.J., Fei-Fei, L.: MentorNet: regularizing very deep neural networks on corrupted labels. arXiv preprint arXiv:1712.05055 (2017)
Joulin, A., van der Maaten, L., Jabri, A., Vasilache, N.: Learning visual features from large weakly supervised data. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 67–84. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_5
Krause, J., et al.: The unreasonable effectiveness of noisy data for fine-grained recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 301–320. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_19
Lee, K.H., He, X., Zhang, L., Yang, L.: CleanNet: transfer learning for scalable image classifier training with label noise. arXiv preprint arXiv:1711.07131 (2017)
Lee, K.H., He, X., Zhang, L., Yang, L.: CleanNet: transfer learning for scalable image classifier training with label noise. In: CVPR, pp. 5447–5456 (2018)
Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Learning to learn from noisy labeled data. In: CVPR, June 2019
Li, Q., Peng, X., Cao, L., Du, W., Xing, H., Qiao, Y.: Product image recognition with guidance learning and noisy supervision. Comput. Vis. Image Underst. 196, 102963 (2020)
Li, W., Wang, L., Li, W., Agustsson, E., Van Gool, L.: Webvision database: visual learning and understanding from web data. arXiv preprint arXiv:1708.02862 (2017)
Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, L.J.: Learning from noisy labels with distillation. In: ICCV, pp. 1928–1936 (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
Mai, Z., Hu, G., Chen, D., Shen, F., Shen, H.T.: MetaMixUp: learning adaptive interpolation policy of MixUp with meta-learning. arXiv preprint arXiv:1908.10059 (2019)
Manwani, N., Sastry, P.: Noise tolerance under risk minimization. IEEE Trans. Cybern. 43(3), 1146–1151 (2013)
Miranda, A.L.B., Garcia, L.P.F., Carvalho, A.C.P.L.F., Lorena, A.C.: Use of classification algorithms in noise detection and elimination. In: Corchado, E., Wu, X., Oja, E., Herrero, Á., Baruque, B. (eds.) HAIS 2009. LNCS (LNAI), vol. 5572, pp. 417–424. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-02319-4_50
Misra, I., Lawrence Zitnick, C., Mitchell, M., Girshick, R.: Seeing through the human reporting bias: visual classifiers from noisy human-centric labels. In: CVPR, pp. 2930–2939 (2016)
Patrini, G., Rozza, A., Menon, A.K., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: CVPR, pp. 2233–2241 (2017)
Reed, S., Lee, H., Anguelov, D., Szegedy, C., Erhan, D., Rabinovich, A.: Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596 (2014)
Rolnick, D., Veit, A., Belongie, S., Shavit, N.: Deep learning is robust to massive label noise. arXiv preprint arXiv:1705.10694 (2017)
Schmidt, R.A., Bjork, R.A.: New conceptualizations of practice: common principles in three paradigms suggest new concepts for training. Psychol. Sci. 3(4), 207–218 (1992)
Sukhbaatar, S., Bruna, J., Paluri, M., Bourdev, L., Fergus, R.: Training convolutional networks with noisy labels. arXiv preprint arXiv:1406.2080 (2014)
Tanaka, D., Ikami, D., Yamasaki, T., Aizawa, K.: Joint optimization framework for learning with noisy labels. arXiv preprint arXiv:1803.11364 (2018)
Veit, A., Alldrin, N., Chechik, G., Krasin, I., Gupta, A., Belongie, S.J.: Learning from noisy large-scale datasets with minimal supervision, In: CVPR. pp. 6575–6583 (2017)
Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states, pp. 6438–6447 (2019)
Wang, K., Peng, X., Yang, J., Lu, S., Qiao, Y.: Suppressing uncertainties for large-scale facial expression recognition. In: CVPR, June 2020
Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: CVPR, pp. 2691–2699 (2015)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
Zhang, W., Wang, Y., Qiao, Y.: MetaCleaner: learning to hallucinate clean representations for noisy-labeled visual recognition. In: CVPR, pp. 7373–7382 (2019)
Zhuang, B., Liu, L., Li, Y., Shen, C., Reid, I.: Attend in groups: a weakly-supervised deep learning framework for learning from web data. In: CVPR, pp. 1878–1887 (2017)
Acknowledge
This work is partially supported by National Key Research and Development Program of China (No. 2020YFC2004800), National Natural Science Foundation of China (U1813218, U1713208), Science and Technology Service Network Initiative of Chinese Academy of Sciences (KFJ-STS-QYZX-092), Guangdong Special Support Program (2016TX03X276), and Shenzhen Basic Research Program (JSGG20180507182100698, CXB201104220032A), Shenzhen Institute of Artificial Intelligence and Robotics for Society.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Peng, X., Wang, K., Zeng, Z., Li, Q., Yang, J., Qiao, Y. (2020). Suppressing Mislabeled Data via Grouping and Self-attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12361. Springer, Cham. https://doi.org/10.1007/978-3-030-58517-4_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-58517-4_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58516-7
Online ISBN: 978-3-030-58517-4
eBook Packages: Computer ScienceComputer Science (R0)