Self-paced Robust Deep Face Recognition with Label Noise

  • Pengfei Zhu
  • Wenya Ma
  • Qinghua HuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11441)


Deep face recognition has achieved rapid development but still suffers from occlusions, illumination and pose variations, especially for face identification. The success of deep learning models in face recognition lies in large-scale high quality face data with accurate labels. However, in real-world applications, the collected data may be mixed with severe label noise, which significantly degrades the generalization ability of deep models. To alleviate the impact of label noise on face recognition, inspired by curriculum learning, we propose a self-paced deep learning model (SPDL) by introducing a negative \(l_1\)-norm regularizer for face recognition with label noise. During training, SPDL automatically evaluates the cleanness of samples in each batch and chooses cleaner samples for training while abandons the noisy samples. To demonstrate the effectiveness of SPDL, we use deep convolution neural network architectures for the task of robust face recognition. Experimental results show that our SPDL achieves superior performance on LFW, MegaFace and YTF when there are different levels of label noise.


Face recognition Label noise Self-pace learning 



This work was supported by the National Natural Science Foundation of China under Grants 61502332, 61876127 and 61732011, Natural Science Foundation of Tianjin Under Grants 17JCZDJC30800.


  1. 1.
    Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41–48. ACM (2009)Google Scholar
  2. 2.
    Brodley, C.E., Friedl, M.A., et al.: Identifying and eliminating mislabeled training instances. In: Proceedings of the National Conference on Artificial Intelligence, pp. 799–805 (1996)Google Scholar
  3. 3.
    Deng, J., Guo, J., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. arXiv preprint arXiv:1801.07698 (2018)
  4. 4.
    Gao, W., Wang, L., Li, Y.F., Zhou, Z.H.: Risk minimization in the presence of label noise. In: AAAI, pp. 1575–1581 (2016)Google Scholar
  5. 5.
    Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87–102. Springer, Cham (2016). Scholar
  6. 6.
    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
  7. 7.
    Huang, G.B., Jain, V., Learned-Miller, E.: Unsupervised joint alignment of complex images. In: ICCV (2007)Google Scholar
  8. 8.
    Huang, W., Gu, J.J., Ma, X., Li, Y.: Self-paced model learning for robust visual tracking. J. Electron. Imaging 26(1), 013016 (2017)CrossRefGoogle Scholar
  9. 9.
    Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)
  10. 10.
    Jiang, L., Meng, D., Zhao, Q., Shan, S., Hauptmann, A.G.: Self-paced curriculum learning. In: AAAI, vol. 2, p. 6 (2015)Google Scholar
  11. 11.
    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. 2309–2318 (2018)Google Scholar
  12. 12.
    Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The MegaFace benchmark: 1 million faces for recognition at scale. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4873–4882 (2016)Google Scholar
  13. 13.
    Lapedriza, A., Pirsiavash, H., Bylinskii, Z., Torralba, A.: Are all training examples equally valuable? arXiv preprint arXiv:1311.6510 (2013)
  14. 14.
    Lee, Y.J., Grauman, K.: Learning the easy things first: self-paced visual category discovery. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1721–1728. IEEE (2011)Google Scholar
  15. 15.
    Li, C., Wei, F., Yan, J., Zhang, X., Liu, Q., Zha, H.: A self-paced regularization framework for multilabel learning. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2660–2666 (2018)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Ng, H.W., Winkler, S.: A data-driven approach to cleaning large face datasets. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 343–347. IEEE (2014)Google Scholar
  17. 17.
    Patrini, G., Nielsen, F., Nock, R., Carioni, M.: Loss factorization, weakly supervised learning and label noise robustness. In: International Conference on Machine Learning, pp. 708–717 (2016)Google Scholar
  18. 18.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)Google Scholar
  19. 19.
    Wang, H., Wang, Q., Gao, M., Li, P., Zuo, W.: Multi-scale location-aware kernel representation for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1248–1257 (2018)Google Scholar
  20. 20.
    Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. arXiv preprint arXiv:1801.09414 (2018)
  21. 21.
    Wolf, L., Hassner, T., Maoz, I.: Face recognition in unconstrained videos with matched background similarity. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 529–534. IEEE (2011)Google Scholar
  22. 22.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987–5995. IEEE (2017)Google Scholar
  23. 23.
    Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014)
  24. 24.
    Zhang, J., Sheng, V.S., Li, T., Wu, X.: Improving crowdsourced label quality using noise correction. IEEE Trans. Neural Netw. Learn. Syst. 29(5), 1675–1688 (2018)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Zhang, Y., Wang, L., Qi, J., Wang, D., Feng, M., Lu, H.: Structured siamese network for real-time visual tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 355–370. Springer, Cham (2018). Scholar
  26. 26.
    Zhou, S., et al.: Deep self-paced learning for person re-identification. Pattern Recogn. 76, 739–751 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.College of Intelligence and ComputingTianjin UniversityTianjinChina

Personalised recommendations