Open Access
REVIEW
Survey on the Loss Function of Deep Learning in Face Recognition
Jun Wang1, Suncheng Feng2,*, Yong Cheng3, Najla Al-Nabhan4
1 Director of Science and Technology Industry Department, Nanjing University of Information Science & Technology, Nanjing, China
2 School of Computer & Software, Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science & Technology, Nanjing, China
3 Science and Technology Industry Department, Nanjing University of Information Science & Technology, Nanjing, China
4 Deptratment of Computer Science, King Saud University, Riyadh, Saudi Arabia
* Corresponding Author: Suncheng Feng. Email:
Journal of Information Hiding and Privacy Protection 2021, 3(1), 29-45. https://doi.org/10.32604/jihpp.2021.016835
Received 13 January 2021; Accepted 28 March 2021; Issue published 21 April 2021
Abstract
With the continuous development of face recognition network, the
selection of loss function plays an increasingly important role in improving
accuracy. The loss function of face recognition network needs to minimize the
intra-class distance while expanding the inter-class distance. So far, one of our
mainstream loss function optimization methods is to add penalty terms, such as
orthogonal loss, to further constrain the original loss function. The other is to
optimize using the loss based on angular/cosine margin. The last is Triplet loss
and a new type of joint optimization based on HST Loss and ACT Loss. In this
paper, based on the three methods with good practical performance and the joint
optimization method, various loss functions are thoroughly reviewed.
Keywords
Cite This Article
J. Wang, S. Feng, Y. Cheng and N. Al-Nabhan, "Survey on the loss function of deep learning in face recognition,"
Journal of Information Hiding and Privacy Protection, vol. 3, no.1, pp. 29–45, 2021. https://doi.org/10.32604/jihpp.2021.016835
Citations