Bridging Human Concepts and Computer Vision for Explainable Face Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Doh, Miriam, Rodrigues, Caroline Mazini, Boutry, Nicolas, Najman, Laurent, Mancas, Matei, Bersini, Hugues
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917613641138176
author Doh, Miriam
Rodrigues, Caroline Mazini
Boutry, Nicolas
Najman, Laurent
Mancas, Matei
Bersini, Hugues
author_facet Doh, Miriam
Rodrigues, Caroline Mazini
Boutry, Nicolas
Najman, Laurent
Mancas, Matei
Bersini, Hugues
contents With Artificial Intelligence (AI) influencing the decision-making process of sensitive applications such as Face Verification, it is fundamental to ensure the transparency, fairness, and accountability of decisions. Although Explainable Artificial Intelligence (XAI) techniques exist to clarify AI decisions, it is equally important to provide interpretability of these decisions to humans. In this paper, we present an approach to combine computer and human vision to increase the explanation's interpretability of a face verification algorithm. In particular, we are inspired by the human perceptual process to understand how machines perceive face's human-semantic areas during face comparison tasks. We use Mediapipe, which provides a segmentation technique that identifies distinct human-semantic facial regions, enabling the machine's perception analysis. Additionally, we adapted two model-agnostic algorithms to provide human-interpretable insights into the decision-making processes.
format Preprint
id arxiv_https___arxiv_org_abs_2403_08789
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bridging Human Concepts and Computer Vision for Explainable Face Verification
Doh, Miriam
Rodrigues, Caroline Mazini
Boutry, Nicolas
Najman, Laurent
Mancas, Matei
Bersini, Hugues
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
With Artificial Intelligence (AI) influencing the decision-making process of sensitive applications such as Face Verification, it is fundamental to ensure the transparency, fairness, and accountability of decisions. Although Explainable Artificial Intelligence (XAI) techniques exist to clarify AI decisions, it is equally important to provide interpretability of these decisions to humans. In this paper, we present an approach to combine computer and human vision to increase the explanation's interpretability of a face verification algorithm. In particular, we are inspired by the human perceptual process to understand how machines perceive face's human-semantic areas during face comparison tasks. We use Mediapipe, which provides a segmentation technique that identifies distinct human-semantic facial regions, enabling the machine's perception analysis. Additionally, we adapted two model-agnostic algorithms to provide human-interpretable insights into the decision-making processes.
title Bridging Human Concepts and Computer Vision for Explainable Face Verification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2403.08789