Instance-Consistent Fair Face Recognition

doi:10.1109/TPAMI.2025.3545781

	Instance-Consistent Fair Face Recognition
	Li, Yong 1; Sun, Yufei 2; Cui, Zhen 3; Shen, Pengcheng 4; Shan, Shiguang 5,6
	2025-07-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	47 期号:7 页码:5319-5335
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.
关键词	Face recognition Training Measurement Annotations Accuracy Benchmark testing Electronic mail Sun Standards Loss measurement biometrics fairness adaptive margin
DOI	10.1109/TPAMI.2025.3545781
收录类别	SCI
语种	英语
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
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001504146900046
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42354
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.Southeast Univ, Sch Comp Sci & Engn, Key Lab New Generat Artificial Intelligence Techno, Nanjing 210096, Peoples R China 2.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China 3.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, 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.Univ Chinese Acad Sci, Beijing 100049, 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.