Abstract
Biometric authentication has become one of the most widely used tools in the current technological era to authenticate users and to distinguish between genuine users and imposters. Face is the most common form of biometric modality that has proven effective. Deep learning-based face recognition systems are now commonly used across different domains. However, these systems usually operate like black-box models that do not provide necessary explanations or justifications for their decisions. This is a major disadvantage because users cannot trust such artificial intelligence-based biometric systems and may not feel comfortable using them when clear explanations or justifications are not provided. This paper addresses this problem by applying an efficient method for explainable face recognition systems. We use a Class Activation Mapping (CAM)-based discriminative localization (very narrow/specific localization) technique called Scaled Directed Divergence (SDD) to visually explain the results of deep learning-based face recognition systems. We perform fine localization of the face features relevant to the deep learning model for its prediction/decision. Our experiments show that the SDD Class Activation Map (CAM) highlights the relevant face features very specifically compared to the traditional CAM and very accurately. The provided visual explanations with narrow localization of relevant features can ensure much-needed transparency and trust for deep learning-based face recognition systems.
Abstract (translated)
生物特征认证已成为当前技术时代中最广泛使用的工具之一，用于验证用户身份并区分真实用户和冒充者。面部是最常见的生物识别模式，已被证明非常有效。基于深度学习的面部识别系统如今在不同领域中被广泛应用。然而，这些系统通常像黑箱模型一样运作，无法提供决策背后的必要解释或理由。这是一大劣势，因为用户无法信任此类基于人工智能的生物识别系统，并且当没有提供清晰的解释时可能会感到不舒适使用它们。本文通过应用一种用于可解释面部识别系统的高效方法来解决这个问题。我们采用了一种名为尺度定向分歧（Scaled Directed Divergence, SDD）的技术，这是一种基于类激活映射（Class Activation Mapping, CAM）的区分性定位技术，用于对基于深度学习的面部识别系统的结果进行视觉说明。我们在实验中进行了精细定位，确定了与深度学习模型预测/决策相关的面部特征。我们的实验证明，SDD 类激活图比传统的CAM更具体地突出了相关面部特征，并且准确性更高。所提供的具有狭窄局部化特性的可视化解释可以确保基于深度学习的面部识别系统的所需透明度和信任度。
URL
https://arxiv.org/abs/2505.03837
