Skip to main content

Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13672))

Included in the following conference series:

Abstract

Recent studies have highlighted the problem of noisy labels in large scale in-the-wild facial expressions datasets due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators. To solve the problem of noisy labels, we propose Soft Label Smoothing (SLS), which smooths out multiple high-confidence classes in the logits by assigning them a probability based on the corresponding confidence, and at the same time assigning a fixed low probability to the low-confidence classes. Specifically, we introduce what we call the Smooth Operator Framework for Teaching (SOFT), based on a mean-teacher (MT) architecture where SLS is applied over the teacher’s logits. We find that the smoothed teacher’s logit provides a beneficial supervision to the student via a consistency loss – at 30% noise rate, SLS leads to 15% reduction in the error rate compared with MT. Overall, SOFT beats the state of the art at mitigating noisy labels by a significant margin for both symmetric and asymmetric noise. Our code is available at https://github.com/toharl/soft.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

References

  1. Albanie, S., Nagrani, A., Vedaldi, A., Zisserman, A.: Emotion recognition in speech using cross-modal transfer in the wild. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 292–301 (2018)

    Google Scholar 

  2. Barsoum, E., Zhang, C., Ferrer, C.C., Zhang, Z.: Training deep networks for facial expression recognition with crowd-sourced label distribution. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction, pp. 279–283 (2016)

    Google Scholar 

  3. Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  4. Blanchard, G., Flaska, M., Handy, G., Pozzi, S., Scott, C.: Classification with asymmetric label noise: consistency and maximal denoising. Electron. J. Stat. 10(2), 2780–2824 (2016)

    Article  MathSciNet  Google Scholar 

  5. Chen, S., Wang, J., Chen, Y., Shi, Z., Geng, X., Rui, Y.: Label distribution learning on auxiliary label space graphs for facial expression recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13984–13993 (2020)

    Google Scholar 

  6. Chen, X., Gupta, A.: Webly supervised learning of convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1431–1439 (2015)

    Google Scholar 

  7. Chen, Y., Wang, J., Chen, S., Shi, Z., Cai, J.: Facial motion prior networks for facial expression recognition. In: 2019 IEEE Visual Communications and Image Processing (VCIP), pp. 1–4. IEEE (2019)

    Google Scholar 

  8. Cheung, W., Hamarneh, G.: \( n \)-sift: \( n \)-dimensional scale invariant feature transform. IEEE Trans. Image Process. 18(9), 2012–2021 (2009)

    Article  MathSciNet  Google Scholar 

  9. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886–893. IEEE (2005)

    Google Scholar 

  10. Dolhansky, B., et al.: The deepfake detection challenge (DFDC) dataset. arXiv preprint arXiv:2006.07397 (2020)

  11. Farzaneh, A.H., Qi, X.: Discriminant distribution-agnostic loss for facial expression recognition in the wild. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 406–407 (2020)

    Google Scholar 

  12. Gao, B.B., Xing, C., Xie, C.W., Wu, J., Geng, X.: Deep label distribution learning with label ambiguity. IEEE Trans. Image Process. 26(6), 2825–2838 (2017)

    Article  MathSciNet  Google Scholar 

  13. Geng, X.: Label distribution learning. IEEE Trans. Knowl. Data Eng. 28(7), 1734–1748 (2016)

    Article  Google Scholar 

  14. Geng, X., Qian, X., Huo, Z., Zhang, Y.: Head pose estimation based on multivariate label distribution. IEEE Trans. Pattern Anal. Mach. Intell. (2020)

    Google Scholar 

  15. Geng, X., Yin, C., Zhou, Z.H.: Facial age estimation by learning from label distributions. IEEE Trans. Pattern Anal. Mach. Intell. 35(10), 2401–2412 (2013)

    Article  Google Scholar 

  16. Ghosh, A., Kumar, H., Sastry, P.: Robust loss functions under label noise for deep neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)

    Google Scholar 

  17. Goldberger, J., Ben-Reuven, E.: Training deep neural-networks using a noise adaptation layer (2016)

    Google Scholar 

  18. Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)

    Google Scholar 

  19. Goodfellow, I.J., et al.: Challenges in representation learning: a report on three machine learning contests. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8228, pp. 117–124. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-42051-1_16

    Chapter  Google Scholar 

  20. Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)

  21. Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271–21284 (2020)

    Google Scholar 

  22. Han, B., et al.: Masking: a new perspective of noisy supervision. In: Advances in Neural Information Processing Systems, vol. 31 (2018)

    Google Scholar 

  23. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)

    Google Scholar 

  24. 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 

  25. Hendrycks, D., Mazeika, M., Wilson, D., Gimpel, K.: Using trusted data to train deep networks on labels corrupted by severe noise. In: Advances in Neural Information Processing Systems, vol. 31 (2018)

    Google Scholar 

  26. Hou, P., Geng, X., Zhang, M.L.: Multi-label manifold learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)

    Google Scholar 

  27. Hu, W., Huang, Y., Zhang, F., Li, R.: Noise-tolerant paradigm for training face recognition CNNs. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11887–11896 (2019)

    Google Scholar 

  28. Jenni, S., Favaro, P.: Deep bilevel learning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 618–633 (2018)

    Google Scholar 

  29. Kervadec, C., Vielzeuf, V., Pateux, S., Lechervy, A., Jurie, F.: Cake: compact and accurate k-dimensional representation of emotion. arXiv preprint arXiv:1807.11215 (2018)

  30. Kim, Y., Yoo, B., Kwak, Y., Choi, C., Kim, J.: Deep generative-contrastive networks for facial expression recognition. arXiv preprint arXiv:1703.07140 (2017)

  31. Krogh, A., Hertz, J.: Ba simple weight decay can improve generalization. In: Moody, J.E., Hanson, S.J., Lippmann, R.P. (eds.) Advances in Neural Information Processing Systems, vol. 4 (1992)

    Google Scholar 

  32. Li, S., Deng, W., Du, J.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2852–2861 (2017)

    Google Scholar 

  33. Li, Y.K., Zhang, M.L., Geng, X.: Leveraging implicit relative labeling-importance information for effective multi-label learning. In: 2015 IEEE International Conference on Data Mining, pp. 251–260. IEEE (2015)

    Google Scholar 

  34. Liu, C., Wechsler, H.: Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Trans. Image Process. 11(4), 467–476 (2002)

    Article  Google Scholar 

  35. 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 

  36. Lukasik, M., Bhojanapalli, S., Menon, A., Kumar, S.: Does label smoothing mitigate label noise? In: International Conference on Machine Learning, pp. 6448–6458. PMLR (2020)

    Google Scholar 

  37. Malach, E., Shalev-Shwartz, S.: Decoupling “when to update” from “how to update”. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  38. Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18–31 (2017)

    Article  Google Scholar 

  39. 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)

  40. 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 

  41. Reed, S., Lee, H., Anguelov, D., Szegedy, C., Erhan, D., Rabinovich, A.: Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596 (2014)

  42. Ruan, D., Yan, Y., Lai, S., Chai, Z., Shen, C., Wang, H.: Feature decomposition and reconstruction learning for effective facial expression recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7660–7669 (2021)

    Google Scholar 

  43. Shan, C., Gong, S., McOwan, P.W.: Facial expression recognition based on local binary patterns: a comprehensive study. Image Vis. Comput. 27(6), 803–816 (2009)

    Article  Google Scholar 

  44. She, J., Hu, Y., Shi, H., Wang, J., Shen, Q., Mei, T.: Dive into ambiguity: latent distribution mining and pairwise uncertainty estimation for facial expression recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6248–6257 (2021)

    Google Scholar 

  45. Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)

    Article  Google Scholar 

  46. 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 

  47. Song, H., Kim, M., Park, D., Shin, Y., Lee, J.G.: Learning from noisy labels with deep neural networks: a survey. arXiv preprint arXiv:2007.08199 (2020)

  48. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  49. Sukhbaatar, S., Bruna, J., Paluri, M., Bourdev, L., Fergus, R.: Training convolutional networks with noisy labels. arXiv preprint arXiv:1406.2080 (2014)

  50. Sun, N., Li, Q., Huan, R., Liu, J., Han, G.: Deep spatial-temporal feature fusion for facial expression recognition in static images. Pattern Recogn. Lett. 119, 49–61 (2019)

    Article  Google Scholar 

  51. 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 

  52. Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780 (2017)

  53. Wang, C., Wang, S., Liang, G.: Identity-and pose-robust facial expression recognition through adversarial feature learning. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 238–246 (2019)

    Google Scholar 

  54. Wang, K., Peng, X., Yang, J., Lu, S., Qiao, Y.: Suppressing uncertainties for large-scale facial expression recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6897–6906 (2020)

    Google Scholar 

  55. Wang, K., Peng, X., Yang, J., Meng, D., Qiao, Y.: Region attention networks for pose and occlusion robust facial expression recognition. IEEE Trans. Image Process. 29, 4057–4069 (2020)

    Article  Google Scholar 

  56. Wang, R., Liu, T., Tao, D.: Multiclass learning with partially corrupted labels. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2568–2580 (2017)

    Article  MathSciNet  Google Scholar 

  57. Wen, Z., Lin, W., Wang, T., Xu, G.: Distract your attention: multi-head cross attention network for facial expression recognition. arXiv preprint arXiv:2109.07270 (2021)

  58. Xia, X., et al.: Robust early-learning: hindering the memorization of noisy labels. In: International Conference on Learning Representations (2020)

    Google Scholar 

  59. 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 

  60. Xu, N., Liu, Y.P., Geng, X.: Label enhancement for label distribution learning. IEEE Trans. Knowl. Data Eng. 33(4), 1632–1643 (2019)

    Article  Google Scholar 

  61. Yang, H., Ciftci, U., Yin, L.: Facial expression recognition by de-expression residue learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2168–2177 (2018)

    Google Scholar 

  62. Zeng, J., Shan, S., Chen, X.: Facial expression recognition with inconsistently annotated datasets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 222–237 (2018)

    Google Scholar 

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

  64. Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)

    Article  Google Scholar 

  65. Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: Advances in Neural Information Processing Systems, vol. 31 (2018)

    Google Scholar 

  66. Zhao, Z., Liu, Q., Zhou, F.: Robust lightweight facial expression recognition network with label distribution training. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 3510–3519 (2021)

    Google Scholar 

  67. Zhong, L., Liu, Q., Yang, P., Liu, B., Huang, J., Metaxas, D.N.: Learning active facial patches for expression analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2562–2569. IEEE (2012)

    Google Scholar 

  68. Zhou, Y., Xue, H., Geng, X.: Emotion distribution recognition from facial expressions. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1247–1250 (2015)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Tohar Lukov .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 88 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

Lukov, T., Zhao, N., Lee, G.H., Lim, SN. (2022). Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions. 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 13672. Springer, Cham. https://doi.org/10.1007/978-3-031-19775-8_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19775-8_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19774-1

  • Online ISBN: 978-3-031-19775-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics