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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Instance-Consistent Fair Face Recognition

文献类型：期刊论文

作者Li, Yong3; Sun, Yufei2; Cui, Zhen6; Shen, Pengcheng4; Shan, Shiguang1,5
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2025-07-01
卷号47期号:7页码:5319-5335
关键词Face recognition Training Measurement Annotations Accuracy Benchmark testing Electronic mail Sun Standards Loss measurement biometrics fairness adaptive margin
ISSN号0162-8828
DOI10.1109/TPAMI.2025.3545781
英文摘要The fairness of face recognition (FR) is a challenging issue to numerous FR algorithms in the modern pluralistic and egalitarian society. In this work, we propose an instance-consistent fair face recognition (IC-FFR) method by fulfilling complete instance fairness on false positive rate (FPR) and true positive rate (TPR). In view of the misalignment of testing and training metrics, not yet considered by the current fair FR algorithms, in theory, we inspect the correlation between the testing metrics (FPR and TPR) and the label classification loss, and we derive a high-probability consistency of unfairness penalties from FPR and TPR to the softmax loss. According to the theoretical analysis, we further develop an instance-consistent fairness solution by introducing customized instance margins, which well preserve consistent FPR and TPR of all instances during the label classification in training. To encourage more fine-grained fairness evaluation, we contribute a dataset called national faces in the world (NFW) to measure the fairness of individuals and countries. Extensive experiments on our NFW as well as the RFW and BFW benchmarks demonstrate the effectiveness and superiority of our method compared to those state-of-the-art fair FR methods.
资助项目Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0680202] ; National Natural Science Foundation of China[62476133]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001504146900046
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/42353]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Cui, Zhen; Shan, Shiguang
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China
3.Southeast Univ, Sch Comp Sci & Engn, Key Lab New Generat Artificial Intelligence Techno, Nanjing 210096, Peoples R China
4.Momenta, Suzhou 215000, Peoples R China
5.Chinese Acad Sci, Inst Comp Technol, State Key Lab AI Safety, Beijing 100190, Peoples R China
6.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China
推荐引用方式
GB/T 7714		 Li, Yong,Sun, Yufei,Cui, Zhen,et al. Instance-Consistent Fair Face Recognition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2025,47(7):5319-5335.
APA Li, Yong,Sun, Yufei,Cui, Zhen,Shen, Pengcheng,&Shan, Shiguang.(2025).Instance-Consistent Fair Face Recognition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,47(7),5319-5335.
MLA Li, Yong,et al."Instance-Consistent Fair Face Recognition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 47.7(2025):5319-5335.

入库方式： OAI收割

来源：计算技术研究所

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。