The search functionality is under construction.
The search functionality is under construction.

Gradient-Enhanced Softmax for Face Recognition

Linjun SUN, Weijun LI, Xin NING, Liping ZHANG, Xiaoli DONG, Wei HE

  • Full Text Views

    0

  • Cite this

Summary :

This letter proposes a gradient-enhanced softmax supervisor for face recognition (FR) based on a deep convolutional neural network (DCNN). The proposed supervisor conducts the constant-normalized cosine to obtain the score for each class using a combination of the intra-class score and the soft maximum of the inter-class scores as the objective function. This mitigates the vanishing gradient problem in the conventional softmax classifier. The experiments on the public Labeled Faces in the Wild (LFW) database denote that the proposed supervisor achieves better results when compared with those achieved using the current state-of-the-art softmax-based approaches for FR.

Publication
IEICE TRANSACTIONS on Information Vol.E103-D No.5 pp.1185-1189
Publication Date
2020/05/01
Publicized
2020/02/07
Online ISSN
1745-1361
DOI
10.1587/transinf.2019EDL8103
Type of Manuscript
LETTER
Category
Artificial Intelligence, Data Mining

Authors

Linjun SUN
  Chinese Academy of Sciences,University of Chinese Academy of Sciences
Weijun LI
  Chinese Academy of Sciences,University of Chinese Academy of Sciences
Xin NING
  Chinese Academy of Sciences,University of Chinese Academy of Sciences
Liping ZHANG
  Chinese Academy of Sciences,University of Chinese Academy of Sciences
Xiaoli DONG
  Chinese Academy of Sciences,University of Chinese Academy of Sciences
Wei HE
  Cognitive Computing Technology Joint Laboratory

Keyword