Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sarkar, Syamantak, Bora, Revoti P., Kaushal, Bhupender, George, Sudhish N, Raja, Kiran
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.18154
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915462166609920
author Sarkar, Syamantak
Bora, Revoti P.
Kaushal, Bhupender
George, Sudhish N
Raja, Kiran
author_facet Sarkar, Syamantak
Bora, Revoti P.
Kaushal, Bhupender
George, Sudhish N
Raja, Kiran
contents Class Activation Maps (CAMs) are one of the important methods for visualizing regions used by deep learning models. Yet their robustness to different noise remains underexplored. In this work, we evaluate and report the resilience of various CAM methods for different noise perturbations across multiple architectures and datasets. By analyzing the influence of different noise types on CAM explanations, we assess the susceptibility to noise and the extent to which dataset characteristics may impact explanation stability. The findings highlight considerable variability in noise sensitivity for various CAMs. We propose a robustness metric for CAMs that captures two key properties: consistency and responsiveness. Consistency reflects the ability of CAMs to remain stable under input perturbations that do not alter the predicted class, while responsiveness measures the sensitivity of CAMs to changes in the prediction caused by such perturbations. The metric is evaluated empirically across models, different perturbations, and datasets along with complementary statistical tests to exemplify the applicability of our proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability
Sarkar, Syamantak
Bora, Revoti P.
Kaushal, Bhupender
George, Sudhish N
Raja, Kiran
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Class Activation Maps (CAMs) are one of the important methods for visualizing regions used by deep learning models. Yet their robustness to different noise remains underexplored. In this work, we evaluate and report the resilience of various CAM methods for different noise perturbations across multiple architectures and datasets. By analyzing the influence of different noise types on CAM explanations, we assess the susceptibility to noise and the extent to which dataset characteristics may impact explanation stability. The findings highlight considerable variability in noise sensitivity for various CAMs. We propose a robustness metric for CAMs that captures two key properties: consistency and responsiveness. Consistency reflects the ability of CAMs to remain stable under input perturbations that do not alter the predicted class, while responsiveness measures the sensitivity of CAMs to changes in the prediction caused by such perturbations. The metric is evaluated empirically across models, different perturbations, and datasets along with complementary statistical tests to exemplify the applicability of our proposed approach.
title Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.18154