Advertisement

Weighted Softmax Loss for Face Recognition via Cosine Distance

  • Hu Zhang
  • Xianliang Wang
  • Zhixiang He
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)

Abstract

Softmax loss is commonly used to train convolutional neural networks (CNNs), but it treats all samples equally. Focal loss focus on training hard samples and takes the probability as the measurement of whether the sample is easy or hard one. In this paper, we use cosine distance of features and the corresponding centers as weight and propose weighted softmax loss (called C-Softmax). Unlike focal loss, we give greater weight to easy samples. Experiment results show that the proposed C-Softmax loss can train many well known models like ResNet, ResNeXt, DenseNet and Inception V3, and the performance of the proposed loss is better than softmax loss and focal loss.

Keywords

Face recognition Focal loss Softmax loss C-Softmax loss 

References

  1. 1.
    Wen, Y., Zhang, K., Li, Z., Qiao, Y.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46478-7_31CrossRefGoogle Scholar
  2. 2.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)Google Scholar
  3. 3.
    Hadsell, R., Chopra, S., Lecun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1735–1742 (2006)Google Scholar
  4. 4.
    Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: ICML, pp. 507–516 (2016)Google Scholar
  5. 5.
    Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–220 (2017)Google Scholar
  6. 6.
    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. arXiv preprint arXiv:1708 (2017)
  7. 7.
    Liu, Y., Li, H., Wang, X.: Rethinking feature discrimination and polymerization for large-scale recognition. arXiv preprint arXiv:1710.00870 (2017)
  8. 8.
    Wang, F., Xiang, X., Cheng, J., Yuille, A.L.: NormFace: L2 hypersphere embedding for face verification. arXiv preprint arXiv:1704.06369 (2017)
  9. 9.
    Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014)
  10. 10.
    Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report, University of Massachusetts (2007)Google Scholar
  11. 11.
    Paszke, A., Gross, S., Chintala, S., Chanan, G.: PyTorch: tensors and dynamic neural networks in Python with strong GPU acceleration (2017)Google Scholar
  12. 12.
    Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Sig. Process. Lett. 23, 1499–1503 (2016)CrossRefGoogle Scholar
  13. 13.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  14. 14.
    Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)
  15. 15.
    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
  16. 16.
    Wang, F., Liu, W., Liu, H., Cheng, J.: Additive margin softmax for face verification. arXiv preprint arXiv:1801.05599 (2018)
  17. 17.
    Kemelmachershlizerman, 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
  18. 18.
    Huang, G.B., Learned-Miller, E.: Labeled faces in the wild: updates and new reporting procedures. Technical report, Department of Computer Science, University of Massachusetts Amherst, Amherst (2014)Google Scholar
  19. 19.
    Liao, S., Lei, Z., Yi, D., Li, S.Z.: A benchmark study of large-scale unconstrained face recognition. In: 2014 IEEE International Joint Conference on Biometrics (IJCB), pp. 1–8 (2014)Google Scholar
  20. 20.
    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).  https://doi.org/10.1007/978-3-319-46487-9_6CrossRefGoogle Scholar
  21. 21.
    Hu, W., Huang, Y., Zhang, F., Li, R., Li, W., Yuan, G.: SeqFace: make full use of sequence information for face recognition. arXiv preprint arXiv:1803.06524 (2018)
  22. 22.
    Deng, J., Guo, J., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. arXiv preprint arXiv:1801.07698 (2018)
  23. 23.
    Wan, W., Zhong, Y., Li, T., Chen, J.: Rethinking feature distribution for loss functions in image classification. arXiv preprint arXiv:1803.02988 (2018)
  24. 24.
    Zheng, Y., Pal, D.K., Savvides, M.: Ring loss: convex feature normalization for face recognition. arXiv preprint arXiv:1803.00130 (2018)
  25. 25.
    Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. arXiv preprint arXiv:1801.09414 (2018)
  26. 26.
    Liu, J., Deng, Y., Bai, T., Wei, Z., Huang, C.: Targeting ultimate accuracy: face recognition via deep embedding. arXiv preprint arXiv:1506.07310 (2015)
  27. 27.
    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 (2015)Google Scholar
  28. 28.
    Huang, G., Liu, Z., Weinberger, K.Q., Laurens, V.D.M.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1 (2017)Google Scholar
  29. 29.
    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, pp. 5987–5995 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Beijing Hisign Corp., Ltd.BeijingChina

Personalised recommendations