mlsanityData to 7 Oct 2026

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

arXiv 2104.10252 ↗First posted 20 Apr 2021cs.CVcited by 25

Not on the map. Why?

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.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 30 of its 35 references that are in the map. First posted on arXiv 20 Apr 2021.

Builds on

30 of 35 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  12. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
18 more
  1. 2018Sanity Checks for Saliency Mapscited by 1,149
  2. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  3. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  4. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  5. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  6. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  7. 2019Counterfactual Visual Explanationscited by 312
  8. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  9. 2016What do different evaluation metrics tell us about saliency models?cited by 184
  10. 2016Generating Visual Explanationscited by 156
  11. 2020Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNscited by 151
  12. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  13. 2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
  14. 2018Grounding Visual Explanationscited by 92
  15. 2016Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Modelcited by 91
  16. 2019Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networkscited by 49
  17. 2020SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localizationcited by 46
  18. 2020IS-CAM: Integrated Score-CAM for axiomatic-based explanationscited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 6; 2024: 6; 2025: 4; 2026: 4.

25 papers.

Sort:

By area:

  1. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  2. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  3. 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
  4. 2025JAFAR: Jack up Any Feature at Any Resolutioncited by 21
  5. 2024Global Counterfactual Directionscited by 15
  6. 2022medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Spacecited by 10
  7. 2024Auditing Local Explanations is Hardcited by 8
  8. 2025CAMs as Shapley Value-based Explainerscited by 5
  9. 2023ViT-ReciproCAM: Gradient and Attention-Free Visual Explanations for Vision Transformercited by 4
  10. 2024CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretationcited by 4
  11. 2024Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approachcited by 4
  12. 2022Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networkscited by 3
13 more
  1. 2022Local Interpretable Model Agnostic Shap Explanations for machine learning modelscited by 3
  2. 2023Overview of Class Activation Maps for Visualization Explainabilitycited by 2
  3. 2023On the stability, correctness and plausibility of visual explanation methods based on feature importancecited by 2
  4. 2024Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestrycited by 2
  5. 2023Improving Mass Detection in Mammography Images: A Study of Weakly Supervised Learning and Class Activation Map Methodscited by 1
  6. 2023Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidancecited by 1
  7. 2026SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretabilitycited by 1
  8. 2024IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Studycited by 0
  9. 2025TraNCE: Transformative Non-linear Concept Explainer for CNNscited by 0
  10. 2025Explainable Image Classification with Reduced Overconfidence for Tissue Characterisationcited by 0
  11. 2026DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debuggingcited by 0
  12. 2026H-SemiS: Hierarchical Fusion of Semi and Self-Supervised Learning for Knee Osteoarthritis Severity Gradingcited by 0
  13. 2026How to Evaluate and Refine your CAMcited by 0