Mis-Classified Vector Guided Softmax Loss for Face Recognition

Authors

  • Xiaobo Wang JD AI Research
  • Shifeng Zhang CASIA
  • Shuo Wang JD AI Research
  • Tianyu Fu JD AI Research
  • Hailin Shi JD AI Research
  • Tao Mei JD AI Research

DOI:

https://doi.org/10.1609/aaai.v34i07.6906

Abstract

Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (e.g., angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our code is available at http://www.cbsr.ia.ac.cn/users/xiaobowang/.

Downloads

Published

2020-04-03

How to Cite

Wang, X., Zhang, S., Wang, S., Fu, T., Shi, H., & Mei, T. (2020). Mis-Classified Vector Guided Softmax Loss for Face Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12241-12248. https://doi.org/10.1609/aaai.v34i07.6906

Issue

Section

AAAI Technical Track: Vision