Abstract
Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. The key success of LNL lies in identifying as many clean samples as possible from massive noisy data, while rectifying the wrongly assigned noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. To mitigate this issue, we propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors. Specifically, our method is divided into two steps: 1) Neighborhood Collective Noise Verification to separate all training samples into a clean or noisy subset, 2) Neighborhood Collective Label Correction to relabel noisy samples, and then auxiliary techniques are used to assist further model optimization. Extensive experiments on four commonly used benchmark datasets, i.e., CIFAR-10, CIFAR-100, Clothing-1M and Webvision-1.0, demonstrate that our proposed method considerably outperforms state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Algan, G., Ulusoy, I.: Image classification with deep learning in the presence of noisy labels: a survey. Knowl. Based Syst. 215, 106771 (2021)
Arazo, E., Ortego, D., Albert, P., O’Connor, N.E., McGuinness, K.: Pseudo-labeling and confirmation bias in deep semi-supervised learning. In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE (2020)
Arazo, E., Ortego, D., Albert, P., O’Connor, N., McGuinness, K.: Unsupervised label noise modeling and loss correction. In: International Conference on Machine Learning, pp. 312–321. PMLR (2019)
Bahri, D., Jiang, H., Gupta, M.: Deep k-NN for noisy labels. In: III, H.D., Singh, A. (ed.) Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 119, pp. 540–550. PMLR (2020)
Bendre, N., Marín, H.T., Najafirad, P.: Learning from few samples: a survey. arXiv preprint arXiv:2007.15484 (2020)
Chen, Y., Shen, X., Hu, S.X., Suykens, J.A.: Boosting co-teaching with compression regularization for label noise. In: CVPR Learning from Limited and Imperfect Data (L2ID) workshop (2021)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 113–123 (2019)
Englesson, E., Azizpour, H.: Consistency regularization can improve robustness to label noise. arXiv preprint arXiv:2110.01242 (2021)
Gunel, B., Du, J., Conneau, A., Stoyanov, V.: Supervised contrastive learning for pre-trained language model fine-tuning. In: International Conference on Learning Representations (2020)
Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: NeurIPS, pp. 8535–8545 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Huang, L., Zhang, C., Zhang, H.: Self-adaptive training: beyond empirical risk minimization. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Huang, Z., et al.: Learning with noisy correspondence for cross-modal matching. In: Advances in Neural Information Processing Systems, vol. 34, pp. 29406–29419 (2021)
Jiang, L., Huang, D., Liu, M., Yang, W.: Beyond synthetic noise: deep learning on controlled noisy labels. In: International Conference on Machine Learning, pp. 4804–4815. PMLR (2020)
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)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Master’s thesis, University of Tront (2009)
Kun, Y., Jianxin, W.: Probabilistic end-to-end noise correction for learning with noisy labels. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Li, J., Li, G., Shi, Y., Yu, Y.: Cross-domain adaptive clustering for semi-supervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2505–2514 (2021)
Li, J., Socher, R., Hoi, S.C.: Dividemix: learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394 (2020)
Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Learning to learn from noisy labeled data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5051–5059 (2019)
Li, J., Xiong, C., Hoi, S.C.: Learning from noisy data with robust representation learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9485–9494 (2021)
Li, W., Li, F., Luo, Y., Wang, P., et al.: Deep domain adaptive object detection: a survey. In: 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1808–1813. IEEE (2020)
Li, W., Wang, L., Li, W., Agustsson, E., Gool, L.V.: Webvision database: visual learning and understanding from web data. Arxiv Preprint (2017)
Liu, S., Niles-Weed, J., Razavian, N., Fernandez-Granda, C.: Early-learning regularization prevents memorization of noisy labels. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Ma, X., et al.: Dimensionality-driven learning with noisy labels. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 80, pp. 3355–3364. PMLR (2018)
Ma, Z., Leijon, A.: Bayesian estimation of beta mixture models with variational inference. IEEE Trans. Pattern Anal. Mach. Intell. 33(11), 2160–2173 (2011)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579–2605 (2008)
Malach, E., Shalev-Shwartz, S.: Decoupling“ when to update” from“ how to update”. In: Advances in Neural Information Processing Systems , vol. 30, pp. 960–970 (2017)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 26. Curran Associates, Inc. (2013). https://proceedings.neurips.cc/paper/2013/file/9aa42b31882ec039965f3c4923ce901b-Paper.pdf
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)
Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
Ortego, D., Arazo, E., Albert, P., O’Connor, N.E., McGuinness, K.: Multi-objective interpolation training for robustness to label noise. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6606–6615 (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 Conference on Computer Vision and Pattern Recognition, pp. 1944–1952 (2017)
Permuter, H., Francos, J., Jermyn, I.: A study of gaussian mixture models of color and texture features for image classification and segmentation. Pattern Recogn. 39(4), 695–706 (2006)
Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. In: International Conference on Machine Learning, pp. 4334–4343. PMLR (2018)
Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Song, H., Kim, M., Lee, J.G.: Selfie: refurbishing unclean samples for robust deep learning. In: International Conference on Machine Learning, pp. 5907–5915. 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)
Tanaka, D., Ikami, D., Yamasaki, T., Aizawa, K.: Joint optimization framework for learning with noisy labels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5552–5560 (2018)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 1195–1204 (2017)
Van Engelen, J.E., Hoos, H.H.: A survey on semi-supervised learning. Mach. Learn. 109(2), 373–440 (2020)
Wang, Y., et al.: Iterative learning with open-set noisy labels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8688–8696 (2018)
Wu, P., Zheng, S., Goswami, M., Metaxas, D.N., Chen, C.: A topological filter for learning with label noise. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Wu, Z.F., Wei, T., Jiang, J., Mao, C., Tang, M., Li, Y.F.: NGC: a unified framework for learning with open-world noisy data (2021)
Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2691–2699 (2015)
Yang, M., Huang, Z., Hu, P., Li, T., Lv, J., Peng, X.: Learning with twin noisy labels for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14308–14317 (2022)
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., Sugiyama, M.: How does disagreement help generalization against label corruption? In: International Conference on Machine Learning, pp. 7164–7173. PMLR (2019)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
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)
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. Nat. Mach. Intell. 4(1), 32–40 (2022)
Zhu, Z., Song, Y., Liu, Y.: Clusterability as an alternative to anchor points when learning with noisy labels. In: International Conference on Machine Learning, pp. 12912–12923. PMLR (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 Guangzhou Science and technology project (No. 202102020633), and in part by Hong Kong Research Grants Council through Research Impact Fund (Grant R-5001-18).
Author information
Authors and Affiliations
Corresponding authors
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
Li, J., Li, G., Liu, F., Yu, Y. (2022). Neighborhood Collective Estimation for Noisy Label Identification and Correction. 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_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-20053-3_8
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)