DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching

2026-09-14

AI Summary

本文提出DenseFace方法，通过密度感知的概率匹配减少预训练面部识别模型中的种族偏见，同时保持识别精度。

Abstract

Despite steady progress in face recognition, current face recognition models still suffer from significant demographic biases. While approaches for bias mitigation have been proposed, existing methods often impose constraints on the training procedure and result in the degradation of recognition accuracy. To address this issue, we here introduce a method that reduces racial bias in pre-trained face recognition models without compromising their accuracy. To this end, we model face embeddings of each person by von Mises-Fisher (MF) distribution. We next observe the dependency between demographic attributes and the density of MF distributions, and propose DenseFace, a probabilistic face matching procedure that accounts for differences in MF distributions. Our extensive experiments demonstrate DenseFace to consistently reduce racial bias in strong face recognition models varying in network architectures, training datasets and loss functions. Notably, DenseFace preserves recognition accuracy and requires no retraining of the underlying face recognition model. Our work also investigates previously adopted bias measures and makes suggestions.

Problem

• racial bias
• face recognition
• bias mitigation
• recognition accuracy

Innovation

• Density-Aware Probabilistic Matching
• von Mises-Fisher Distribution
• Bias Mitigation
• Face Recognition
• Racial Bias