Publication
Title
On the coherency of quantitative evaluation of visual explanations
Author
Abstract
Recent years have shown an increased development of methods for justifying the predictions of neural networks through visual explanations. These explanations usually take the form of heatmaps which assign a saliency (or relevance) value to each pixel of the input image that expresses how relevant the pixel is for the prediction of a label. Complementing this development, evaluation methods have been proposed to assess the “goodness” of such explanations. On the one hand, some of these methods rely on synthetic datasets. However, this introduces the weakness of having limited guarantees regarding their applicability on more realistic settings. On the other hand, some methods rely on metrics for objective evaluation. However the level to which some of these evaluation methods perform with respect to each other is uncertain. Taking this into account, we conduct a comprehensive study on a subset of the ImageNet-1k validation set where we evaluate a number of different commonly-used explanation methods following a set of evaluation methods. We complement our study with sanity checks on the studied evaluation methods as a means to investigate their reliability and the impact of characteristics of the explanations on the evaluation methods. Results of our study suggest that there is a lack of coherency on the grading provided by some of the considered evaluation methods. Moreover, we have identified some characteristics of the explanations, e.g. sparsity, which can have a significant effect on the performance.
Language
English
Source (journal)
Computer vision and image understanding. - -
Publication
2024
ISSN
1077-3142
DOI
10.1016/J.CVIU.2024.103934
Volume/pages
241 (2024) , p. 1-9
Article Reference
103934
ISI
001181796700001
Full text (Publisher's DOI)
Full text (open access)
The author-created version that incorporates referee comments and is the accepted for publication version Available from 05.08.2024
Full text (publisher's version - intranet only)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identifier
Creation 22.03.2024
Last edited 08.05.2024
To cite this reference