Skip to content

Latest commit

 

History

History
62 lines (62 loc) · 2.43 KB

2025-01-14-zhang25a.md

File metadata and controls

62 lines (62 loc) · 2.43 KB
title booktitle year volume series month publisher pdf url openreview abstract layout issn id tex_title firstpage lastpage page order cycles bibtex_editor editor bibtex_author author date address container-title genre issued extras
Saliency Maps Give a False Sense of Explanability to Image Classifiers: An Empirical Evaluation across Methods and Metrics
Proceedings of the 16th Asian Conference on Machine Learning
2025
260
Proceedings of Machine Learning Research
0
PMLR
Hftgajppmz
The interpretability of deep neural networks (DNNs) has emerged as a crucial area of research, particularly in image classification tasks where decisions often lack transparency. Saliency maps have been widely used as a tool to decode the inner workings of these networks by highlighting regions of input images deemed most influential in the classification process. However, recent studies have revealed significant limitations and inconsistencies in the utility of saliency maps as explanations. This paper aims to systematically assess the shortcomings of saliency maps and explore alternative approaches to achieve more reliable and interpretable explanations for image classification models. We carry out a series of experiments to show that 1) the existing evaluation does not provide a fair nor meaningful comparison to the existing saliency maps; these evaluations have their implicit assumption and are not differentiable; 2) the saliency maps do not provide enough information on explaining the accuracy of network, the relationship between classes and the modification of the images.
inproceedings
2640-3498
zhang25a
{Saliency Maps Give a False Sense of Explanability to Image Classifiers}: {A}n Empirical Evaluation across Methods and Metrics
479
494
479-494
479
false
Nguyen, Vu and Lin, Hsuan-Tien
given family
Vu
Nguyen
given family
Hsuan-Tien
Lin
Zhang, Hanwei and Figueroa, Felipe Torres and Hermanns, Holger
given family
Hanwei
Zhang
given family
Felipe Torres
Figueroa
given family
Holger
Hermanns
2025-01-14
Proceedings of the 16th Asian Conference on Machine Learning
inproceedings
date-parts
2025
1
14