Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention

TL;DR

This paper introduces GABN, a novel method that reduces racial bias in face recognition by aligning gradient attention maps across races and enlarging sensitive facial regions, leading to more equitable performance.

Contribution

The paper proposes a gradient attention-based de-bias method that balances facial region focus across races, improving fairness in face recognition systems.

Findings

GABN reduces racial bias in face recognition.

GABN achieves more balanced performance across races.

The method enlarges sensitive regions for darker-skinned individuals.

Abstract

Although face recognition has made impressive progress in recent years, we ignore the racial bias of the recognition system when we pursue a high level of accuracy. Previous work found that for different races, face recognition networks focus on different facial regions, and the sensitive regions of darker-skinned people are much smaller. Based on this discovery, we propose a new de-bias method based on gradient attention, called Gradient Attention Balance Network (GABN). Specifically, we use the gradient attention map (GAM) of the face recognition network to track the sensitive facial regions and make the GAMs of different races tend to be consistent through adversarial learning. This method mitigates the bias by making the network focus on similar facial regions. In addition, we also use masks to erase the Top-N sensitive facial regions, forcing the network to allocate its attention to a larger facial region. This method expands the sensitive region of darker-skinned people and further reduces the gap between GAM of darker-skinned people and GAM of Caucasians. Extensive experiments show that GABN successfully mitigates racial bias in face recognition and learns more balanced performance for people of different races.