Advertisement

Learning with Noisy Class Labels for Instance Segmentation

Conference paper
  • 607 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12359)

Abstract

Instance segmentation has achieved siginificant progress in the presence of correctly annotated datasets. Yet, object classes in large-scale datasets are sometimes ambiguous, which easily causes confusion. In addition, limited experience and knowledge of annotators can also lead to mislabeled object classes. To solve this issue, a novel method is proposed in this paper, which uses different losses describing different roles of noisy class labels to enhance the learning. Specifically, in instance segmentation, noisy class labels play different roles in the foreground-background sub-task and the foreground-instance sub-task. Hence, on the one hand, the noise-robust loss (e.g., symmetric loss) is used to prevent incorrect gradient guidance for the foreground-instance sub-task. On the other hand, standard cross entropy loss is used to fully exploit correct gradient guidance for the foreground-background sub-task. Extensive experiments conducted with three popular datasets (i.e., Pascal VOC, Cityscapes and COCO) have demonstrated the effectiveness of our method in a wide range of noisy class labels scenarios. Code will be available at: github.com/longrongyang/LNCIS.

Keywords

Noisy class labels Instance segmentation Foreground-instance sub-task Foreground-background sub-task 

Notes

Acknowledgement

This work was supported in part by National Natural Science Foundation of China (No.61831005, 61525102, 61871087 and 61971095).

References

  1. 1.
    Arpit, D., et al.: A closer look at memorization in deep networks. In: ICML (2017)Google Scholar
  2. 2.
    Box, G.E.P., Cox, D.R.: An analysis of transformations. J. Roy. Stat. Soc.: Ser. B (Methodol.) 26(2), 211–243 (1964)zbMATHGoogle Scholar
  3. 3.
    Chen, K., et al.: Hybrid task cascade for instance segmentation. In: CVPR (2019)Google Scholar
  4. 4.
    Chen, K., et al.: MMdetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)
  5. 5.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)Google Scholar
  6. 6.
    De Brabandere, B., Neven, D., Van Gool, L.: Semantic instance segmentation with a discriminative loss function. arXiv preprint arXiv:1708.02551 (2017)
  7. 7.
    Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303–338 (2010)CrossRefGoogle Scholar
  8. 8.
    Ghosh, A., Kumar, H., Sastry, P.: Robust loss functions under label noise for deep neural networks. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  9. 9.
    Ghosh, A., Manwani, N., Sastry, P.: Making risk minimization tolerant to label noise. Neurocomputing 160, 93–107 (2015)CrossRefGoogle Scholar
  10. 10.
    Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)Google Scholar
  11. 11.
    Gygli, M., Ferrari, V.: Fast object class labelling via speech. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5365–5373 (2019)Google Scholar
  12. 12.
    Han, B., et al.: Masking: a new perspective of noisy supervision. In: Advances in Neural Information Processing Systems, pp. 5836–5846 (2018)Google Scholar
  13. 13.
    Han, B., 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
  14. 14.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988. IEEE (2017)Google Scholar
  15. 15.
    Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X.: Mask scoring R-CNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6409–6418 (2019)Google Scholar
  16. 16.
    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. arXiv preprint arXiv:1712.05055 (2017)
  17. 17.
    Lee, K.H., He, X., Zhang, L., Yang, L.: Cleannet: transfer learning for scalable image classifier training with label noise. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5447–5456 (2018)Google Scholar
  18. 18.
    Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, L.J.: Learning from noisy labels with distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1910–1918 (2017)Google Scholar
  19. 19.
    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_48CrossRefGoogle Scholar
  20. 20.
    Liu, Y., et al.: Affinity derivation and graph merge for instance segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 708–724. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_42CrossRefGoogle Scholar
  21. 21.
    Ma, X., et al.: Dimensionality-driven learning with noisy labels. arXiv preprint arXiv:1806.02612 (2018)
  22. 22.
    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
  23. 23.
    Pereyra, G., Tucker, G., Chorowski, J., Kaiser, Ł., Hinton, G.: Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548 (2017)
  24. 24.
    Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8430–8439 (2019)Google Scholar
  25. 25.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar
  26. 26.
    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
  27. 27.
    Vahdat, A.: Toward robustness against label noise in training deep discriminative neural networks. In: Advances in Neural Information Processing Systems, pp. 5596–5605 (2017)Google Scholar
  28. 28.
    Veit, A., Alldrin, N., Chechik, G., Krasin, I., Gupta, A., Belongie, S.: Learning from noisy large-scale datasets with minimal supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 839–847 (2017)Google Scholar
  29. 29.
    Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., Bailey, J.: Symmetric cross entropy for robust learning with noisy labels. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 322–330 (2019)Google Scholar
  30. 30.
    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
  31. 31.
    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 (2019)Google Scholar
  32. 32.
    Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. In: ICLR (2017)Google Scholar
  33. 33.
    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

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Information and Communication EngineeringUniversity of Electronic Science and Technology of ChinaChengduChina

Personalised recommendations