中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 生物识别与安全技术研究中心
RVFace: Reliable Vector Guided Softmax Loss for Face Recognition

文献类型：期刊论文

作者Wang, Xiaobo4,5,6; Wang, Shuo3; Liang, Yanyan4; Gu, Liang6; Lei, Zhen1,2,5
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2022
卷号31页码:2337-2351
关键词Deep face recognition noisy labels detection margin-based softmax loss mining-based softmax loss discriminative feature learning
ISSN号1057-7149
DOI10.1109/TIP.2022.3154293
通讯作者Liang, Yanyan(yyliang@must.edu.mo)
英文摘要Face recognition has witnessed significant progress with the advances of deep convolutional neural networks (CNNs), and the central task of which is how to improve the feature discrimination. To this end, several margin-based (e.g., angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from four issues: 1) They are based on the assumption of well-cleaned training sets, without considering the consequence of noisy labels inherently existing in most of face recognition datasets; 2) They ignore the importance of informative (e.g., semi-hard) features mining for discriminative learning; 3) They encourage the feature margin only from the perspective of ground truth class, without realizing the discriminability from other non-ground truth classes; and 4) They set the feature margin between different classes to be same and fixed, which may not adapt the situation of unbalanced data in different classes very well. To cope with these issues, this paper develops a novel loss function, which explicitly estimates the noisy labels to drop them and adaptively emphasizes the semi-hard feature vectors from the remaining reliable ones to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative features for face recognition. 'lb the best of our knowledge, this is the first attempt to inherit the advantages of feature-based noisy labels detection, feature mining and feature margin into a unified loss function. Extensive experimental results on a variety of face recognition benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our source code is available at http://www.cbsr.ia.ac.cn/users/xiaobowang/.
资助项目National Key Research and Development Program[2020YFC2003901] ; Chinese National Natural Science Foundation[62106264] ; Chinese National Natural Science Foundation[61876178] ; Chinese National Natural Science Foundation[61976229] ; Chinese National Natural Science Foundation[62176256] ; Science and Technology Development Fund of Macau[0008/2019/A1] ; Science and Technology Development Fund of Macau[0010/2019/AFJ] ; Science and Technology Development Fund of Macau[0025/2019/AKP] ; Science and Technology Development Fund of Macau[0004/2020/A1] ; Science and Technology Development Fund of Macau[0070/2021/AMJ] ; Guangdong Provincial Key Research and Development Program[2019B010148001]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000769973200002
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program ; Chinese National Natural Science Foundation ; Science and Technology Development Fund of Macau ; Guangdong Provincial Key Research and Development Program
源URL[http://ir.ia.ac.cn/handle/173211/48093]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
通讯作者Liang, Yanyan
作者单位1.Chinese Acad Sci, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong, Peoples R China
2.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Chinese Acad Sci CASIA, Inst Automat, Beijing 100190, Peoples R China
4.Macau Univ Sci & Technol, Fac Informat Technol, Taipa, Macau, Peoples R China
5.Chinese Acad Sci CASIA, Inst Automat, Ctr Biometr & Secur Res CBSR, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
6.Sangfor Technol Inc, Shenzhen 518052, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Xiaobo,Wang, Shuo,Liang, Yanyan,et al. RVFace: Reliable Vector Guided Softmax Loss for Face Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:2337-2351.
APA Wang, Xiaobo,Wang, Shuo,Liang, Yanyan,Gu, Liang,&Lei, Zhen.(2022).RVFace: Reliable Vector Guided Softmax Loss for Face Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,2337-2351.
MLA Wang, Xiaobo,et al."RVFace: Reliable Vector Guided Softmax Loss for Face Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):2337-2351.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。