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.

翻译：尽管近年来人脸识别取得了令人瞩目的进展，但我们在追求高准确率的同时忽略了识别系统中的种族偏见。先前的研究发现，针对不同种族，人脸识别网络关注的区域存在差异，且深色肤色人群的敏感区域显著较小。基于这一发现，我们提出了一种基于梯度注意力的新去偏方法，称为梯度注意力平衡网络（GABN）。具体而言，我们利用人脸识别网络的梯度注意力图（GAM）追踪面部敏感区域，并通过对抗学习使不同种族的GAM趋于一致。该方法通过使网络关注相似的面部区域来缓解偏见。此外，我们还使用掩码擦除前N个敏感面部区域，迫使网络将其注意力分配到更大的面部区域。这扩大了深色肤色人群的敏感区域，并进一步缩小了深色肤色人群与白种人GAM之间的差距。大量实验表明，GABN成功地缓解了人脸识别中的种族偏见，并为不同种族人群学习了更平衡的性能。