Next Article in Journal
A Three-Dimensional Cartesian Mesh Generation Algorithm Based on the GPU Parallel Ray Casting Method
Next Article in Special Issue
Improved Single Sample Per Person Face Recognition via Enriching Intra-Variation and Invariant Features
Previous Article in Journal
Full-Scale Train Derailment Testing and Analysis of Post-Derailment Behavior of Casting Bogie
Previous Article in Special Issue
Deep Learning for Facial Recognition on Single Sample per Person Scenarios with Varied Capturing Conditions
Article

Double Additive Margin Softmax Loss for Face Recognition

College of Information Engineering, Yangzhou University, Yangzhou 225127, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(1), 60; https://doi.org/10.3390/app10010060
Received: 30 October 2019 / Revised: 14 December 2019 / Accepted: 17 December 2019 / Published: 19 December 2019
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Learning large-margin face features whose intra-class variance is small and inter-class diversity is one of important challenges in feature learning applying Deep Convolutional Neural Networks (DCNNs) for face recognition. Recently, an appealing line of research is to incorporate an angular margin in the original softmax loss functions for obtaining discriminative deep features during the training of DCNNs. In this paper we propose a novel loss function, termed as double additive margin Softmax loss (DAM-Softmax). The presented loss has a clearer geometrical explanation and can obtain highly discriminative features for face recognition. Extensive experimental evaluation of several recent state-of-the-art softmax loss functions are conducted on the relevant face recognition benchmarks, CASIA-Webface, LFW, CALFW, CPLFW, and CFP-FP. We show that the proposed loss function consistently outperforms the state-of-the-art. View Full-Text
Keywords: Softmax; angular margin; ResNet; face recognition Softmax; angular margin; ResNet; face recognition
Show Figures

Figure 1

MDPI and ACS Style

Zhou, S.; Chen, C.; Han, G.; Hou, X. Double Additive Margin Softmax Loss for Face Recognition. Appl. Sci. 2020, 10, 60. https://doi.org/10.3390/app10010060

AMA Style

Zhou S, Chen C, Han G, Hou X. Double Additive Margin Softmax Loss for Face Recognition. Applied Sciences. 2020; 10(1):60. https://doi.org/10.3390/app10010060

Chicago/Turabian Style

Zhou, Shengwei, Caikou Chen, Guojiang Han, and Xielian Hou. 2020. "Double Additive Margin Softmax Loss for Face Recognition" Applied Sciences 10, no. 1: 60. https://doi.org/10.3390/app10010060

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop