Mitigating Face Recognition Bias via Group Adaptive Classifier

TL;DR

This paper introduces a novel group adaptive classifier that reduces face recognition bias across demographics by using adaptive kernels and attention mechanisms, improving fairness without sacrificing accuracy.

Contribution

The work proposes a new adaptive convolution and attention-based approach with an automated strategy and de-biasing loss to mitigate demographic bias in face recognition.

Findings

Reduces recognition bias across demographic groups.

Maintains competitive accuracy on standard benchmarks.

Effective in diverse face recognition datasets.

Abstract

Face recognition is known to exhibit bias - subjects in a certain demographic group can be better recognized than other groups. This work aims to learn a fair face representation, where faces of every group could be more equally represented. Our proposed group adaptive classifier mitigates bias by using adaptive convolution kernels and attention mechanisms on faces based on their demographic attributes. The adaptive module comprises kernel masks and channel-wise attention maps for each demographic group so as to activate different facial regions for identification, leading to more discriminative features pertinent to their demographics. Our introduced automated adaptation strategy determines whether to apply adaptation to a certain layer by iteratively computing the dissimilarity among demographic-adaptive parameters. A new de-biasing loss function is proposed to mitigate the gap of average intra-class distance between demographic groups. Experiments on face benchmarks (RFW, LFW, IJB-A, and IJB-C) show that our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.