Abstract
Face recognition (FR) models are vulnerable to performance variations across demographic groups. The causes for these performance differences are unclear due to the highly complex deep learning-based structure of face recognition models. Several works aimed at exploring possible roots of gender and ethnicity bias, identifying semantic reasons such as hairstyle, make-up, or facial hair as possible sources. Motivated by recent discoveries of the importance of frequency patterns in convolutional neural networks, we explain bias in face recognition using state-of-the-art frequency-based explanations. Our extensive results show that different frequencies are important to FR models depending on the ethnicity of the samples.
Abstract (translated)
面部识别（FR）模型在不同的人口群体间表现存在差异，这些性能差距的原因尚不清楚，主要是因为基于深度学习的面部识别模型结构复杂。一些研究试图探索性别和种族偏见的根源，并发现诸如发型、妆容或胡须等语义因素可能是潜在原因。鉴于最近关于卷积神经网络中频率模式重要性的新发现，我们使用先进的基于频率的解释方法来解析面部识别中的偏见问题。我们的研究成果表明，不同的人种样本在面部识别模型中重要的频段是不同的。
URL
https://arxiv.org/abs/2501.16896
