Skip to main content
SpringerLink
Log in

Neighborhood Collective Estimation for Noisy Label Identification and Correction

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13684))

Included in the following conference series:

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.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Algan, G., Ulusoy, I.: Image classification with deep learning in the presence of noisy labels: a survey. Knowl. Based Syst. 215, 106771 (2021)

    Article  Google Scholar 

  2. 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)

    Google Scholar 

  3. 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)

    Google Scholar 

  4. 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)

    Google Scholar 

  5. Bendre, N., Marín, H.T., Najafirad, P.: Learning from few samples: a survey. arXiv preprint arXiv:2007.15484 (2020)

  6. 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)

    Google Scholar 

  7. 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)

    Google Scholar 

  8. Englesson, E., Azizpour, H.: Consistency regularization can improve robustness to label noise. arXiv preprint arXiv:2110.01242 (2021)

  9. 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)

    Google Scholar 

  10. Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: NeurIPS, pp. 8535–8545 (2018)

    Google Scholar 

  11. 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

    Chapter  Google Scholar 

  12. Huang, L., Zhang, C., Zhang, H.: Self-adaptive training: beyond empirical risk minimization. In: Advances in Neural Information Processing Systems, vol. 33 (2020)

    Google Scholar 

  13. 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)

    Google Scholar 

  14. 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)

    Google Scholar 

  15. 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)

    Google Scholar 

  16. Krizhevsky, A.: Learning multiple layers of features from tiny images. Master’s thesis, University of Tront (2009)

    Google Scholar 

  17. 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)

    Google Scholar 

  18. 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)

    Google Scholar 

  19. Li, J., Socher, R., Hoi, S.C.: Dividemix: learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394 (2020)

  20. 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)

    Google Scholar 

  21. 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)

    Google Scholar 

  22. 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)

    Google Scholar 

  23. Li, W., Wang, L., Li, W., Agustsson, E., Gool, L.V.: Webvision database: visual learning and understanding from web data. Arxiv Preprint (2017)

    Google Scholar 

  24. 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)

    Google Scholar 

  25. 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)

    Google Scholar 

  26. Ma, Z., Leijon, A.: Bayesian estimation of beta mixture models with variational inference. IEEE Trans. Pattern Anal. Mach. Intell. 33(11), 2160–2173 (2011)

    Article  Google Scholar 

  27. Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579–2605 (2008)

    MATH  Google Scholar 

  28. 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)

    Google Scholar 

  29. 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

  30. 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)

    Google Scholar 

  31. Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)

  32. 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)

    Google Scholar 

  33. 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)

    Google Scholar 

  34. 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)

    Article  MATH  Google Scholar 

  35. 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)

    Google Scholar 

  36. Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems, vol. 33 (2020)

    Google Scholar 

  37. 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)

    Google Scholar 

  38. 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)

    Google Scholar 

  39. 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)

    Google Scholar 

  40. 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)

    Google Scholar 

  41. Van Engelen, J.E., Hoos, H.H.: A survey on semi-supervised learning. Mach. Learn. 109(2), 373–440 (2020)

    Article  MathSciNet  MATH  Google Scholar 

  42. 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)

    Google Scholar 

  43. 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)

    Google Scholar 

  44. 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)

    Google Scholar 

  45. 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)

    Google Scholar 

  46. 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)

    Google Scholar 

  47. 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)

    Google Scholar 

  48. 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)

    Google Scholar 

  49. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)

  50. 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)

  51. 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)

    Article  Google Scholar 

  52. 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)

    Google Scholar 

Download references

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

  1. Sun Yat-sen University, Guangzhou, 510006, China

    Jichang Li & Guanbin Li

  2. The University of Hong Kong, Hong Kong, China

    Jichang Li & Yizhou Yu

  3. Deepwise AI Lab, Beijing, China

    Feng Liu

Authors
  1. Jichang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guanbin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Feng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yizhou Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Guanbin Li or Yizhou Yu .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 215 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

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)

Publish with us

Policies and ethics

Search

Navigation