Instance-Consistent Fair Face Recognition

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 tr...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 26. Feb.
1. Verfasser: Li, Yong (VerfasserIn)
Weitere Verfasser: Sun, Yufei, Cui, Zhen, Shen, Pengcheng, Shan, Shiguang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM385079958
003 DE-627
005 20250508053537.0
007 cr uuu---uuuuu
008 250508s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3545781  |2 doi 
028 5 2 |a pubmed25n1332.xml 
035 |a (DE-627)NLM385079958 
035 |a (NLM)40031663 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Li, Yong  |e verfasserin  |4 aut 
245 1 0 |a Instance-Consistent Fair Face Recognition 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 03.03.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a 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 
650 4 |a Journal Article 
700 1 |a Sun, Yufei  |e verfasserin  |4 aut 
700 1 |a Cui, Zhen  |e verfasserin  |4 aut 
700 1 |a Shen, Pengcheng  |e verfasserin  |4 aut 
700 1 |a Shan, Shiguang  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2025) vom: 26. Feb.  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:26  |g month:02 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3545781  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 26  |c 02