Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Jae Hee, Mikriukov, Georgii, Schwalbe, Gesina, Wermter, Stefan, Wolter, Diedrich
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929508223811584
author Lee, Jae Hee
Mikriukov, Georgii
Schwalbe, Gesina
Wermter, Stefan
Wolter, Diedrich
author_facet Lee, Jae Hee
Mikriukov, Georgii
Schwalbe, Gesina
Wermter, Stefan
Wolter, Diedrich
contents Concept-based XAI (C-XAI) approaches to explaining neural vision models are a promising field of research, since explanations that refer to concepts (i.e., semantically meaningful parts in an image) are intuitive to understand and go beyond saliency-based techniques that only reveal relevant regions. Given the remarkable progress in this field in recent years, it is time for the community to take a critical look at the advances and trends. Consequently, this paper reviews C-XAI methods to identify interesting and underexplored areas and proposes future research directions. To this end, we consider three main directions: the choice of concepts to explain, the choice of concept representation, and how we can control concepts. For the latter, we propose techniques and draw inspiration from the field of knowledge representation and learning, showing how this could enrich future C-XAI research.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13456
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
Lee, Jae Hee
Mikriukov, Georgii
Schwalbe, Gesina
Wermter, Stefan
Wolter, Diedrich
Computer Vision and Pattern Recognition
Concept-based XAI (C-XAI) approaches to explaining neural vision models are a promising field of research, since explanations that refer to concepts (i.e., semantically meaningful parts in an image) are intuitive to understand and go beyond saliency-based techniques that only reveal relevant regions. Given the remarkable progress in this field in recent years, it is time for the community to take a critical look at the advances and trends. Consequently, this paper reviews C-XAI methods to identify interesting and underexplored areas and proposes future research directions. To this end, we consider three main directions: the choice of concepts to explain, the choice of concept representation, and how we can control concepts. For the latter, we propose techniques and draw inspiration from the field of knowledge representation and learning, showing how this could enrich future C-XAI research.
title Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.13456