For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Gradient-Enhanced Softmax for Face Recognition
Linjun SUN Weijun LI Xin NING Liping ZHANG Xiaoli DONG Wei HE
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2020/05/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
convolutional neural network, face recognition, softmax classifier, vanishing gradient,
Full Text: PDF>>
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.