Deep convolutional neural networks have been pushing the frontier of face recognition (FR) techniques in the past years. Despite the high accuracy, they are often criticized for lacking explainability. There has been an increasing demand for understanding the decision-making process of deep face recognition systems. Recent studies have investigated using visual saliency maps as an explanation, but they often lack a discussion and analysis in the context of face recognition. This paper conceives a new explanation framework for face recognition. It starts by providing a new definition of the saliency-based explanation method, which focuses on the decisions made by the deep FR model. Then, a novel correlation-based RISE algorithm (CorrRISE) is proposed to produce saliency maps, which reveal both the similar and dissimilar regions of any given pair of face images. Besides, two evaluation metrics are designed to measure the performance of general visual saliency explanation methods in face recognition. Consequently, substantial visual and quantitative results have shown that the proposed method consistently outperforms other explainable face recognition approaches.

翻译：深度卷积神经网络近年来不断推动着人脸识别技术的发展前沿。尽管取得了高精度，但这些模型常因缺乏可解释性而受到批评。理解深度人脸识别系统的决策过程需求日益增长。近期研究尝试利用视觉显著性图作为解释手段，但鲜有在人脸识别语境下进行深入讨论与分析。本文提出了一种面向人脸识别的新型解释框架。该框架首先对基于显著性的解释方法给出了新定义，聚焦于深度人脸识别模型的决策机制；随后提出基于相关性的RISE算法（CorrRISE）生成显著性图，能够同时揭示任意给定人脸图像对的相似与差异区域。此外，还设计了两项评估指标用于衡量通用视觉显著性解释方法在人脸识别中的性能。大量的视觉与量化结果表明，本文方法始终优于其他可解释人脸识别方案。