Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shadman, Rashik, Hou, Daqing, Hussain, Faraz, Murshed, M G Sarwar
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.03837
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916723371802624
author Shadman, Rashik
Hou, Daqing
Hussain, Faraz
Murshed, M G Sarwar
author_facet Shadman, Rashik
Hou, Daqing
Hussain, Faraz
Murshed, M G Sarwar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03837
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Explainable Face Recognition via Improved Localization
Shadman, Rashik
Hou, Daqing
Hussain, Faraz
Murshed, M G Sarwar
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Explainable Face Recognition via Improved Localization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.03837