Explainable Face Recognition via Improved Localization

TL;DR

This paper introduces an explainable face recognition method using a novel CAM-based localization technique called SDD, which provides precise visual explanations of face features, enhancing transparency and trust in deep learning systems.

Contribution

The paper proposes a new SDD-based CAM method for fine localization of face features, improving interpretability of deep face recognition models.

Findings

SDD CAM highlights relevant face features more accurately than traditional CAM.

Visual explanations improve transparency and user trust in face recognition systems.

The method demonstrates precise localization of face features relevant to recognition decisions.

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.