Advertisement

A Metric Learning Method Based on Damped Momentum with Threshold

  • Le Zhang
  • Lei Liu
  • Zhiguo Shi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10636)

Abstract

The convolutional neural networks in deep learning have become one of the mainstream algorithms of face recognition technology. Moreover, metric learning is also an important method to train deep learning models, as its ability of verification is very powerful, especially for the face images which are often used in CNNs. Recently, a new type method of metric learning named Center Loss has been proposed. It is simple to use and can enhance the model performance obviously. However, since the updating mechanism of Center Loss is simplistic, it can hardly process large-scale data when the categories are too much. This paper proposes an improved algorithm of Center Loss to accelerate the updating process of feature centers of original algorithm with a damped momentum, which urges deep learning models to have more rapid and steady convergence and better performance. Meanwhile, almost no additional computation cost is added since the new method has an optional threshold. The experimental results show that the improved Center Loss algorithm can further improve the recognition ability of the model, which is very helpful to enhancing the user experience of complex face recognition systems.

Keywords

Deep learning Metric learning Face recognition 

Notes

Acknowledgments

This work was funded by State’s Key Project of Research and Development Plan (2016YFC0901303).

References

  1. 1.
    Lecun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  2. 2.
    Lecun, Y., Boser, B., Denker, J.: Handwritten digit recognition with a back-propagation network. Adv. Neural. Inf. Process. Syst. 2, 396–404 (1997)Google Scholar
  3. 3.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105. Curran Associates Inc. (2012)Google Scholar
  4. 4.
    Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (2016)Google Scholar
  5. 5.
    Szegedy, C., Liu, W., Jia, Y.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015) Google Scholar
  6. 6.
    He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770–778. IEEE (2016)Google Scholar
  7. 7.
    Taigman, Y., Yang, M., Ranzato, M.: DeepFace: closing the gap to human-level performance in face verification. In: Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)Google Scholar
  8. 8.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  9. 9.
    Song, H., Xiang, Y., Jegelka, S.: Deep metric learning via lifted structured feature embedding. Computer Science, pp. 4004–4012 (2015)Google Scholar
  10. 10.
    Wen, Y., Zhang, K., Li, Z.: A discriminative feature learning approach for deep face recognition. In: European Conference on Computer Vision, vol. 47, pp. 499–515. Springer, Cham (2016)Google Scholar
  11. 11.
    Xing, E., Ng, A., Jordan, M.: Distance metric learning, with application to clustering with side-information. Adv. Neural Inf. Process. Syst. 15, 505–512 (2003)Google Scholar
  12. 12.
    Ruder, S.: An overview of gradient descent optimization algorithms (2016)Google Scholar
  13. 13.
    Guo, Y., Zhang, L., Hu, Y.: MS-Celeb-1M: challenge of recognizing one million celebrities in the real world. Electron. Imaging (2016)Google Scholar
  14. 14.
    Sun, Y., Chen, Y., Wang, X.: Deep learning face representation by joint identification-verification. In: Proceedings of Advances in Neural Information Processing Systems, vol. 27, pp. 1988–1996 (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.School of Computer and Communication EngineeringUniversity of Science and Technology BeijingBeijingChina

Personalised recommendations