Papers › Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in...

Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognition

19 Aug 2024arXiv:2408.10175archive 2025-07-28

Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira

This study investigates the effects of occlusions on the fairness of face recognition systems, particularly focusing on demographic biases. Using the Racial Faces in the Wild (RFW) dataset and synthetically added realistic occlusions, we evaluate their effect on the performance of face recognition models trained on the BUPT-Balanced and BUPT-GlobalFace datasets. We note increases in the dispersion of FMR, FNMR, and accuracy alongside decreases in fairness according to Equilized Odds, Demographic Parity, STD of Accuracy, and Fairness Discrepancy Rate. Additionally, we utilize a pixel attribution method to understand the importance of occlusions in model predictions, proposing a new metric, Face Occlusion Impact Ratio (FOIR), that quantifies the extent to which occlusions affect model performance across different demographic groups. Our results indicate that occlusions exacerbate existing demographic biases, with models placing higher importance on occlusions in an unequal fashion, particularly affecting African individuals more severely.

PaperPDFCode

Code

rafaelmmamede/fairness_ocfr officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Face RecognitionFairness

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

STD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections