# Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability

arXiv: https://arxiv.org/abs/2508.18154 · HTML: https://mlsanity.com/paper/2508.18154/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Eigen-CAM: Class Activation Map using Principal Components](https://mlsanity.com/paper/2008.00299/) (2020)
- [The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies](https://mlsanity.com/paper/2007.15911/) (2020)
- [Framework for Evaluating Faithfulness of Local Explanations](https://mlsanity.com/paper/2202.00734/) (2022)

## Abstract (arXiv)

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.