Abstract
Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e. instances of the same class share the same noise model, and are independent of features. While in practice, the real-world noise patterns are usually more fine-grained as instance-dependent ones, which poses a big challenge, especially in the presence of inter-class imbalance. In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge. First, we employ a class-level feature clustering procedure for the early identification of clean samples that are near the class-wise prediction centers. Notably, we address the class imbalance problem by aggregating rare classes according to their prediction entropy. Second, for the remaining clean samples that are close to the ground truth class boundary (usually mixed with the samples with instance-dependent noises), we propose a novel consistency-based classification method that identifies them using the consistency of two classifier heads: the higher the consistency, the larger the probability that a sample is clean. Extensive experiments on several challenging benchmarks demonstrate the superior performance of our method against the state-of-the-art. Code is available at https://github.com/uitrbn/TSCSI_IDN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.: Mixmatch: a holistic approach to semi-supervised learning. arXiv preprint arXiv:1905.02249 (2019)
Chen, P., Liao, B.B., Chen, G., Zhang, S.: Understanding and utilizing deep neural networks trained with noisy labels. In: International Conference on Machine Learning, pp. 1062–1070. PMLR (2019)
Chen, P., Ye, J., Chen, G., Zhao, J., Heng, P.A.: Beyond class-conditional assumption: a primary attempt to combat instance-dependent label noise. arXiv preprint arXiv:2012.05458 (2020)
Chen, P., Ye, J., Chen, G., Zhao, J., Heng, P.A.: Robustness of accuracy metric and its inspirations in learning with noisy labels. arXiv preprint arXiv:2012.04193 (2020)
Cheng, H., Zhu, Z., Li, X., Gong, Y., Sun, X., Liu, Y.: Learning with instance-dependent label noise: a sample sieve approach. arXiv preprint arXiv:2010.02347 (2020)
Cheng, H., Zhu, Z., Li, X., Gong, Y., Sun, X., Liu, Y.: Learning with instance-dependent label noise: a sample sieve approach. In: International Conference on Learning Representations (2021)
Han, et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, pp. 8527–8537 (2018)
Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, pp. 8536–8546 (2018)
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)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp. 1026–1034 (2015)
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)
Hendrycks, D., Mazeika, M., Wilson, D., Gimpel, K.: Using trusted data to train deep networks on labels corrupted by severe noise. arXiv preprint arXiv:1802.05300 (2018)
Jiang, L., Zhou, Z., Leung, T., Li, L.J., Fei-Fei, L.: MentorNet: learning data-driven curriculum for very deep neural networks on corrupted labels. In: International Conference on Machine Learning, pp. 2304–2313. PMLR (2018)
Kim, Y., Yun, J., Shon, H., Kim, J.: Joint negative and positive learning for noisy labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9442–9451 (2021)
Konstantinov, N., Lampert, C.: Robust learning from untrusted sources. In: International Conference on Machine Learning, pp. 3488–3498. PMLR (2019)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Tech. rep, Citeseer (2009)
Li, J., Socher, R., Hoi, S.C.: DivideMix: learning with noisy labels as semi-supervised learning. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=HJgExaVtwr
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)
Liu, T., Tao, D.: Classification with noisy labels by importance reweighting. IEEE Trans. Pattern Anal. Mach. Intell. 38(3), 447–461 (2015)
Liu, Y., Guo, H.: Peer loss functions: learning from noisy labels without knowing noise rates. In: Proceedings of the 37th International Conference on Machine Learning, ICML ’20 (2020)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440 (2015)
Lu, Y., Bo, Y., He, W.: Co-matching: combating noisy labels by augmentation anchoring. arXiv preprint arXiv:2103.12814 (2021)
Ma, X., et al.: Dimensionality-driven learning with noisy labels. In: International Conference on Machine Learning, pp. 3355–3364. PMLR (2018)
Malach, E., Shalev-Shwartz, S.: Decoupling "when to update" from "how to update". In: Advances in Neural Information Processing Systems, pp. 960–970 (2017)
Nguyen, D.T., Mummadi, C.K., Ngo, T.P.N., Nguyen, T.H.P., Beggel, L., Brox, T.: Self: learning to filter noisy labels with self-ensembling. arXiv preprint arXiv:1910.01842 (2019)
Nishi, K., Ding, Y., Rich, A., Hollerer, T.: Augmentation strategies for learning with noisy labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8022–8031 (2021)
Patrini, G., Rozza, A., Krishna Menon, A., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1944–1952 (2017)
Patrini, G., Rozza, A., Krishna Menon, A., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1944–1952 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3723–3732 (2018)
Shen, Y., Sanghavi, S.: Learning with bad training data via iterative trimmed loss minimization. In: International Conference on Machine Learning, pp. 5739–5748. PMLR (2019)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Thirty-first AAAI Conference on Artificial Intelligence (2017)
Thulasidasan, S., Bhattacharya, T., Bilmes, J., Chennupati, G., Mohd-Yusof, J.: Combating label noise in deep learning using abstention. arXiv preprint arXiv:1905.10964 (2019)
Wei, H., Feng, L., Chen, X., An, B.: Combating noisy labels by agreement: a joint training method with co-regularization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13726–13735 (2020)
Xia, X., et al.: Extended T: learning with mixed closed-set and open-set noisy labels. arXiv preprint arXiv:2012.00932 (2020)
Xia, X., et al.: Part-dependent label noise: towards instance-dependent label noise. In: Advances in Neural Information Processing Systems, vol. 33, pp. 7597–7610 (2020)
Xia, X., et al.: Are anchor points really indispensable in label-noise learning? In: Advances in Neural Information Processing Systems, pp. 6838–6849 (2019)
Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2691–2699 (2015)
Xu, Y., Cao, P., Kong, Y., Wang, Y.: L_DMI: a novel information-theoretic loss function for training deep nets robust to label noise. In: Advances in Neural Information Processing Systems, pp. 6222–6233 (2019)
Yao, Y., et al.: Jo-SRC: a contrastive approach for combating noisy labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5192–5201 (2021)
Yu, X., Han, B., Yao, J., Niu, G., Tsang, I.W., Sugiyama, M.: How does disagreement help generalization against label corruption? arXiv preprint arXiv:1901.04215 (2019)
Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: Advances in Neural Information Processing Systems, pp. 8778–8788 (2018)
Zheltonozhskii, E., Baskin, C., Mendelson, A., Bronstein, A.M., Litany, O.: Contrast to divide: self-supervised pre-training for learning with noisy labels. arXiv preprint arXiv:2103.13646 (2021)
Zheng, G., Awadallah, A.H., Dumais, S.: Meta label correction for noisy label learning. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (2021)
Zhou, H.Y., Chen, X., Zhang, Y., Luo, R., Wang, L., Yu, Y.: Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports. Nature Mach. Intell. 4, 32–40 (2022)
Zhu, Z., Liu, T., Liu, Y.: A second-order approach to learning with instance-dependent label noise. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10113–10123 (2021)
Zhu, Z., Song, Y., Liu, Y.: Clusterability as an alternative to anchor points when learning with noisy labels. arXiv preprint arXiv:2102.05291 (2021)
Acknowledgements
This work was supported in part by the Guangdong Basic and Applied Basic Research Foundation (No.2020B1515020048), in part by the National Natural Science Foundation of China (No.61976250, No. U1811463), in part by the Hong Kong Research Grants Council through Research Impact Fund (Grant R-5001-18), and in part by the Guangzhou Science and technology project (No.202102020633).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, G., Li, G., Qin, Y., Liu, F., Yu, Y. (2022). Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels. 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 13685. Springer, Cham. https://doi.org/10.1007/978-3-031-19806-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-19806-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19805-2
Online ISBN: 978-3-031-19806-9
eBook Packages: Computer ScienceComputer Science (R0)