中国科学院深圳先进技术研究院机构知识库(SIAT OpenIR): A Comprehensive Study on Center Loss for Deep Face Recognition
SIAT OpenIR  > 数字所
A Comprehensive Study on Center Loss for Deep Face Recognition
Wen, Yandong; Zhang, Kaipeng; Li, Zhifeng; Qiao, Yu
2019
Source PublicationINTERNATIONAL JOURNAL OF COMPUTER VISION
Subtype期刊论文
AbstractDeep convolutional neural networks (CNNs) trained with the softmax loss have achieved remarkable successes in a number of close-set recognition problems, e.g. object recognition, action recognition, etc. Unlike these close-set tasks, face recognition is an open-set problem where the testing classes (persons) are usually different from those in training. This paper addresses the open-set property of face recognition by developing the center loss. Specifically, the center loss simultaneously learns a center for each class, and penalizes the distances between the deep features of the face images and their corresponding class centers. Training with the center loss enables CNNs to extract the deep features with two desirable properties: inter-class separability and intra-class compactness. In addition, we extend the center loss in two aspects. First, we adopt parameter sharing between the softmax loss and the center loss, to reduce the extra parameters introduced by centers. Second, we generalize the concept of center from a single point to a region in embedding space, which further allows us to account for intra-class variations. The advanced center loss significantly enhances the discriminative power of deep features. Experimental results show that our method achieves high accuracies on several important face recognition benchmarks, including Labeled Faces in the Wild, YouTube Faces, IJB-A Janus, and MegaFace Challenging 1.
Indexed BySCI
Language英语
EI Accession Number多媒体
Document Type期刊论文
Identifierhttp://ir.siat.ac.cn/handle/172644/15698
Collection数字所
Recommended Citation
GB/T 7714
Wen, Yandong,Zhang, Kaipeng,Li, Zhifeng,et al. A Comprehensive Study on Center Loss for Deep Face Recognition[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2019.
APA Wen, Yandong,Zhang, Kaipeng,Li, Zhifeng,&Qiao, Yu.(2019).A Comprehensive Study on Center Loss for Deep Face Recognition.INTERNATIONAL JOURNAL OF COMPUTER VISION.
MLA Wen, Yandong,et al."A Comprehensive Study on Center Loss for Deep Face Recognition".INTERNATIONAL JOURNAL OF COMPUTER VISION (2019).
Files in This Item: Download All
File Name/Size DocType Version Access License
数字-多媒体2019012.pdf(1473KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wen, Yandong]'s Articles
[Zhang, Kaipeng]'s Articles
[Li, Zhifeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wen, Yandong]'s Articles
[Zhang, Kaipeng]'s Articles
[Li, Zhifeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wen, Yandong]'s Articles
[Zhang, Kaipeng]'s Articles
[Li, Zhifeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 数字-多媒体2019012.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.