MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition
This work addresses fairness issues in face recognition for diverse user groups, offering a novel method that is incremental in improving bias reduction without relying on sensitive labels.
The paper tackles demographic bias in face recognition systems by proposing the MixFairFace framework, which introduces a new fairness evaluation protocol and the MixFair Adapter to reduce identity bias without sensitive attribute labels, achieving state-of-the-art fairness performance on benchmark datasets.
Although significant progress has been made in face recognition, demographic bias still exists in face recognition systems. For instance, it usually happens that the face recognition performance for a certain demographic group is lower than the others. In this paper, we propose MixFairFace framework to improve the fairness in face recognition models. First of all, we argue that the commonly used attribute-based fairness metric is not appropriate for face recognition. A face recognition system can only be considered fair while every person has a close performance. Hence, we propose a new evaluation protocol to fairly evaluate the fairness performance of different approaches. Different from previous approaches that require sensitive attribute labels such as race and gender for reducing the demographic bias, we aim at addressing the identity bias in face representation, i.e., the performance inconsistency between different identities, without the need for sensitive attribute labels. To this end, we propose MixFair Adapter to determine and reduce the identity bias of training samples. Our extensive experiments demonstrate that our MixFairFace approach achieves state-of-the-art fairness performance on all benchmark datasets.