Mitigating Face Recognition Bias via Group Adaptive Classifier
This work addresses fairness issues in face recognition systems, which is important for reducing demographic disparities in AI applications, though it appears incremental as it builds on existing methods with specific adaptations.
The paper tackled bias in face recognition by proposing a group adaptive classifier that uses adaptive convolution kernels and attention mechanisms based on demographic attributes, resulting in mitigated bias across groups while maintaining competitive accuracy on benchmarks like RFW, LFW, IJB-A, and IJB-C.
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.