Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/43226
Title: | Evaluating feature attribution methods in the image domain | Authors: | Gevaert, Arne ROUSSEAU, Axel-Jan BECKER, Thijs VALKENBORG, Dirk De Bie, Tijl Saeys, Yvan |
Issue Date: | 2024 | Publisher: | SPRINGER | Source: | Machine learning, | Status: | Early view | Abstract: | Feature attribution maps are a popular approach to highlight the most important pixels in an image for a given prediction of a model. Despite a recent growth in popularity and available methods, the objective evaluation of such attribution maps remains an open problem. Building on previous work in this domain, we investigate existing quality metrics and propose new variants of metrics for the evaluation of attribution maps. We confirm a recent finding that different quality metrics seem to measure different underlying properties of attribution maps, and extend this finding to a larger selection of attribution methods, quality metrics, and datasets. We also find that metric results on one dataset do not necessarily generalize to other datasets, and methods with desirable theoretical properties do not necessarily outperform computationally cheaper alternatives in practice. Based on these findings, we propose a general benchmarking approach to help guide the selection of attribution methods for a given use case. Implementations of attribution metrics and our experiments are available online (https://github.com/arnegevaert/benchmark-general-imaging). | Notes: | Gevaert, A (corresponding author), Univ Ghent, Dept Appl Math Comp Sci & Stat Data Min & Modeling, Technol Pk Zwijnaarde 71, B-9052 Ghent, Belgium. arne.gevaert@ugent.be; axeljan.rousseau@uhasselt.be; thijs.becker@vito.be; dirk.valkenborg@uhasselt.be; tijl.debie@ugent.be; yvan.saeys@ugent.be |
Keywords: | Explainability;Interpretability;Benchmark;Feature attribution;Saliency maps | Document URI: | http://hdl.handle.net/1942/43226 | ISSN: | 0885-6125 | e-ISSN: | 1573-0565 | DOI: | 10.1007/s10994-024-06550-x | ISI #: | 001234023100001 | Rights: | The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. | Category: | A1 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Evaluating feature attribution methods in the image domain.pdf | Early view | 5.74 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.