# Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis

arXiv: https://arxiv.org/abs/2104.10252 · HTML: https://mlsanity.com/paper/2104.10252/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 20 Apr 2021.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [What do different evaluation metrics tell us about saliency models?](https://mlsanity.com/paper/1604.03605/) (2016)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs](https://mlsanity.com/paper/2008.02312/) (2020)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models](https://mlsanity.com/paper/1908.01224/) (2019)
- [Grounding Visual Explanations](https://mlsanity.com/paper/1807.09685/) (2018)
- [Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model](https://mlsanity.com/paper/1611.09571/) (2016)
- [Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1908.02686/) (2019)
- [SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization](https://mlsanity.com/paper/2006.14255/) (2020)
- [IS-CAM: Integrated Score-CAM for axiomatic-based explanations](https://mlsanity.com/paper/2010.03023/) (2020)

## Built on by (most cited first, 25 of 25)

- [HIVE: Evaluating the Human Interpretability of Visual Explanations](https://mlsanity.com/paper/2112.03184/) (2021)
- [Framework for Evaluating Faithfulness of Local Explanations](https://mlsanity.com/paper/2202.00734/) (2022)
- [Opti-CAM: Optimizing saliency maps for interpretability](https://mlsanity.com/paper/2301.07002/) (2023)
- [JAFAR: Jack up Any Feature at Any Resolution](https://mlsanity.com/paper/2506.11136/) (2025)
- [Global Counterfactual Directions](https://mlsanity.com/paper/2404.12488/) (2024)
- [medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space](https://mlsanity.com/paper/2204.05376/) (2022)
- [Auditing Local Explanations is Hard](https://mlsanity.com/paper/2407.13281/) (2024)
- [CAMs as Shapley Value-based Explainers](https://mlsanity.com/paper/2501.06261/) (2025)
- [ViT-ReciproCAM: Gradient and Attention-Free Visual Explanations for Vision Transformer](https://mlsanity.com/paper/2310.02588/) (2023)
- [CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation](https://mlsanity.com/paper/2404.02388/) (2024)
- [Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach](https://mlsanity.com/paper/2411.14946/) (2024)
- [Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networks](https://mlsanity.com/paper/2209.14074/) (2022)
- [Local Interpretable Model Agnostic Shap Explanations for machine learning models](https://mlsanity.com/paper/2210.04533/) (2022)
- [Overview of Class Activation Maps for Visualization Explainability](https://mlsanity.com/paper/2309.14304/) (2023)
- [On the stability, correctness and plausibility of visual explanation methods based on feature importance](https://mlsanity.com/paper/2311.12860/) (2023)
- [Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry](https://mlsanity.com/paper/2402.11670/) (2024)
- [Improving Mass Detection in Mammography Images: A Study of Weakly Supervised Learning and Class Activation Map Methods](https://mlsanity.com/paper/2308.03486/) (2023)
- [Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance](https://mlsanity.com/paper/2312.14201/) (2023)
- [SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability](https://mlsanity.com/paper/2601.12804/) (2026)
- [H-SemiS: Hierarchical Fusion of Semi and Self-Supervised Learning for Knee Osteoarthritis Severity Grading](https://mlsanity.com/paper/2604.23335/) (2026)
- [IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study](https://mlsanity.com/paper/2405.00239/) (2024)
- [TraNCE: Transformative Non-linear Concept Explainer for CNNs](https://mlsanity.com/paper/2503.20230/) (2025)
- [Explainable Image Classification with Reduced Overconfidence for Tissue Characterisation](https://mlsanity.com/paper/2507.23709/) (2025)
- [DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging](https://mlsanity.com/paper/2602.19274/) (2026)
- [How to Evaluate and Refine your CAM](https://mlsanity.com/paper/2605.14641/) (2026)

## Abstract (arXiv)

As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each input pixel with respect to the output of the network. In this paper, we focus on Class Activation Mapping (CAM) approaches, which provide an effective visualization by taking weighted averages of the activation maps. To enhance the evaluation and the reproducibility of such approaches, we propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches. To evaluate the appropriateness of the proposal, we compare different CAM-based visualization methods on the entire ImageNet validation set, fostering proper comparisons and reproducibility.