On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Davoodi, Omid, Mohammadizadehsamakosh, Shayan, Komeili, Majid
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916081232248832
author Davoodi, Omid
Mohammadizadehsamakosh, Shayan
Komeili, Majid
author_facet Davoodi, Omid
Mohammadizadehsamakosh, Shayan
Komeili, Majid
contents Part-prototype networks have recently become methods of interest as an interpretable alternative to many of the current black-box image classifiers. However, the interpretability of these methods from the perspective of human users has not been sufficiently explored. In this work, we have devised a framework for evaluating the interpretability of part-prototype-based models from a human perspective. The proposed framework consists of three actionable metrics and experiments. To demonstrate the usefulness of our framework, we performed an extensive set of experiments using Amazon Mechanical Turk. They not only show the capability of our framework in assessing the interpretability of various part-prototype-based models, but they also are, to the best of our knowledge, the most comprehensive work on evaluating such methods in a unified framework.
format Preprint
id arxiv_https___arxiv_org_abs_2310_06966
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis
Davoodi, Omid
Mohammadizadehsamakosh, Shayan
Komeili, Majid
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Part-prototype networks have recently become methods of interest as an interpretable alternative to many of the current black-box image classifiers. However, the interpretability of these methods from the perspective of human users has not been sufficiently explored. In this work, we have devised a framework for evaluating the interpretability of part-prototype-based models from a human perspective. The proposed framework consists of three actionable metrics and experiments. To demonstrate the usefulness of our framework, we performed an extensive set of experiments using Amazon Mechanical Turk. They not only show the capability of our framework in assessing the interpretability of various part-prototype-based models, but they also are, to the best of our knowledge, the most comprehensive work on evaluating such methods in a unified framework.
title On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2310.06966