Saved in:
Bibliographic Details
Main Authors: Doh, Miriam, Rodrigues, Caroline Mazini, Boutry, N., Najman, L., Mancas, Matei, Gosselin, Bernard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.05471
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929668611899392
author Doh, Miriam
Rodrigues, Caroline Mazini
Boutry, N.
Najman, L.
Mancas, Matei
Gosselin, Bernard
author_facet Doh, Miriam
Rodrigues, Caroline Mazini
Boutry, N.
Najman, L.
Mancas, Matei
Gosselin, Bernard
contents The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to enhance interpretability and transparency. This study extends previous work by integrating semantic concepts derived from human cognitive processes into XAI frameworks to bridge the comprehension gap between model outputs and human understanding. We propose a novel approach combining global and local explanations, using semantic features defined by user-selected facial landmarks to generate similarity maps and textual explanations via large language models (LLMs). The methodology was validated through quantitative experiments and user feedback, demonstrating improved interpretability. Results indicate that our semantic-based approach, particularly the most detailed set, offers a more nuanced understanding of model decisions than traditional methods. User studies highlight a preference for our semantic explanations over traditional pixelbased heatmaps, emphasizing the benefits of human-centric interpretability in AI. This work contributes to the ongoing efforts to create XAI frameworks that align AI models behaviour with human cognitive processes, fostering trust and acceptance in critical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05471
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Found in Translation: semantic approaches for enhancing AI interpretability in face verification
Doh, Miriam
Rodrigues, Caroline Mazini
Boutry, N.
Najman, L.
Mancas, Matei
Gosselin, Bernard
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to enhance interpretability and transparency. This study extends previous work by integrating semantic concepts derived from human cognitive processes into XAI frameworks to bridge the comprehension gap between model outputs and human understanding. We propose a novel approach combining global and local explanations, using semantic features defined by user-selected facial landmarks to generate similarity maps and textual explanations via large language models (LLMs). The methodology was validated through quantitative experiments and user feedback, demonstrating improved interpretability. Results indicate that our semantic-based approach, particularly the most detailed set, offers a more nuanced understanding of model decisions than traditional methods. User studies highlight a preference for our semantic explanations over traditional pixelbased heatmaps, emphasizing the benefits of human-centric interpretability in AI. This work contributes to the ongoing efforts to create XAI frameworks that align AI models behaviour with human cognitive processes, fostering trust and acceptance in critical applications.
title Found in Translation: semantic approaches for enhancing AI interpretability in face verification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2501.05471