Fair Feature Distillation for Visual Recognition

TL;DR

This paper introduces MMD-based Fair Distillation (MFD), a novel feature distillation method that reduces bias and improves fairness in visual recognition models without sacrificing accuracy.

Contribution

It presents the first explicit use of distillation for fairness enhancement in visual recognition and provides theoretical justification for its effectiveness.

Findings

MFD significantly reduces bias against minorities.

MFD maintains high accuracy on face datasets.

Theoretical analysis supports the fairness benefits of MFD.

Abstract

Fairness is becoming an increasingly crucial issue for computer vision, especially in the human-related decision systems. However, achieving algorithmic fairness, which makes a model produce indiscriminative outcomes against protected groups, is still an unresolved problem. In this paper, we devise a systematic approach which reduces algorithmic biases via feature distillation for visual recognition tasks, dubbed as MMD-based Fair Distillation (MFD). While the distillation technique has been widely used in general to improve the prediction accuracy, to the best of our knowledge, there has been no explicit work that also tries to improve fairness via distillation. Furthermore, We give a theoretical justification of our MFD on the effect of knowledge distillation and fairness. Throughout the extensive experiments, we show our MFD significantly mitigates the bias against specific minorities without any loss of the accuracy on both synthetic and real-world face datasets.