Explainable Face Recognition via Improved Localization

2025-05-04

AI Summary

To address the lack of interpretability and low user trust in deep learning–based face recognition systems, this paper proposes Scaled Directed Divergence (SDD), a gradient-guided, fine-grained discriminative region localization method that enhances Class Activation Mapping (CAM). SDD is the first to introduce high-resolution discriminative visualization into face authentication explanation frameworks, significantly improving the precision of critical facial feature localization: explanation consistency exceeds 98.3%, and the average visual activation area shrinks to one-fifth that of conventional CAM. Importantly, SDD requires no model retraining and is fully compatible with mainstream pre-trained face recognition models. By jointly optimizing interpretability, accuracy, and practical deployability, SDD establishes a novel, production-ready explainability paradigm for trustworthy AI-based biometric recognition.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• Improving explainability in face recognition systems
• Enhancing feature localization for transparent AI decisions
• Ensuring trust via visual explanations in biometric authentication

Innovation

• Uses Scaled Directed Divergence for localization
• Fine-tunes face feature localization
• Enhances transparency with visual explanations