Skip to main content
SpringerLink
Log in

Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13685))

Included in the following conference series:

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.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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. 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)

  2. 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)

    Google Scholar 

  3. 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)

  4. 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)

  5. 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)

  6. 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)

    Google Scholar 

  7. 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)

    Google Scholar 

  8. 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)

    Google Scholar 

  9. 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)

    Google Scholar 

  10. 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)

    Google Scholar 

  11. 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)

    Google Scholar 

  12. 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)

  13. 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 

  14. 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)

    Google Scholar 

  15. Konstantinov, N., Lampert, C.: Robust learning from untrusted sources. In: International Conference on Machine Learning, pp. 3488–3498. PMLR (2019)

    Google Scholar 

  16. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Tech. rep, Citeseer (2009)

    Google Scholar 

  17. 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

  18. 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)

  19. Liu, T., Tao, D.: Classification with noisy labels by importance reweighting. IEEE Trans. Pattern Anal. Mach. Intell. 38(3), 447–461 (2015)

    Article  Google Scholar 

  20. 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)

    Google Scholar 

  21. 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)

    Google Scholar 

  22. Lu, Y., Bo, Y., He, W.: Co-matching: combating noisy labels by augmentation anchoring. arXiv preprint arXiv:2103.12814 (2021)

  23. Ma, X., et al.: Dimensionality-driven learning with noisy labels. In: International Conference on Machine Learning, pp. 3355–3364. PMLR (2018)

    Google Scholar 

  24. Malach, E., Shalev-Shwartz, S.: Decoupling "when to update" from "how to update". In: Advances in Neural Information Processing Systems, pp. 960–970 (2017)

    Google Scholar 

  25. 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)

  26. 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 

  27. 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)

    Google Scholar 

  28. 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 

  29. 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)

    Google Scholar 

  30. 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)

    Google Scholar 

  31. 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)

    Google Scholar 

  32. 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 

  33. 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)

  34. 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)

    Google Scholar 

  35. Xia, X., et al.: Extended T: learning with mixed closed-set and open-set noisy labels. arXiv preprint arXiv:2012.00932 (2020)

  36. 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)

    Google Scholar 

  37. Xia, X., et al.: Are anchor points really indispensable in label-noise learning? In: Advances in Neural Information Processing Systems, pp. 6838–6849 (2019)

    Google Scholar 

  38. 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)

    Google Scholar 

  39. 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)

    Google Scholar 

  40. 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 

  41. 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)

  42. 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)

    Google Scholar 

  43. 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)

  44. 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)

    Google Scholar 

  45. 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)

    Article  Google Scholar 

  46. 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)

    Google Scholar 

  47. Zhu, Z., Song, Y., Liu, Y.: Clusterability as an alternative to anchor points when learning with noisy labels. arXiv preprint arXiv:2102.05291 (2021)

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 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

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

    Ganlong Zhao & Guanbin Li

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

    Ganlong Zhao & Yizhou Yu

  3. Cardiff University, Cardiff, UK

    Yipeng Qin

  4. Deepwise AI Lab, Beijing, China

    Feng Liu

Authors
  1. Ganlong Zhao
    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. Yipeng Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Feng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. 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

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

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)

Publish with us

Policies and ethics

Search

Navigation