Distill and De-bias: Mitigating Bias in Face Recognition using Knowledge Distillation. (arXiv:2112.09786v2 [cs.CV] UPDATED)

Face recognition networks generally demonstrate bias with respect to
sensitive attributes like gender, skintone etc. For gender and skintone, we
observe that the regions of the face that a network attends to vary by the
category of an attribute. This might contribute to bias. Building on this
intuition, we propose a novel distillation-based approach called Distill and
De-bias (D&D) to enforce a network to attend to similar face regions,
irrespective of the attribute category. In D&D, we train a teacher …

arxiv bias cv de-bias distillation face recognition knowledge