How to Evaluate and Refine your CAM

Luca Domeniconi; Alessandra Stramiglio; Michele Lombardi; Samuele Salti

cs.CVMay 14, 2026

How to Evaluate and Refine your CAM

Authors: Luca Domeniconi, Alessandra Stramiglio, Michele Lombardi, Samuele Salti

Organizations: University of Bologna, Bologna, Italy

Abstract

Class attribution maps (CAMs) provide local explanations for the decisions of convolutional neural networks. While widely used in practice, the evaluation of CAMs remains challenging due to the lack of ground-truth explanations, making it difficult to evaluate the soundness of existing metrics. Independently, most commonly used CAM methods produce low-resolution attribution maps, which limits their usefulness for detailed interpretability. To address the evaluation challenge, we introduce a synthetic dataset with ground-truth attributions that enables a rigorous comparison of CAM evaluation metrics. Using this dataset, we analyze existing metrics and propose ARCC, a new composite metric that more reliably identifies faithful explanations. To address the low resolution issue, we introduce RefineCAM, a method that produces high-resolution attribution maps by aggregating CAMs across multiple network layers. Our results show that RefineCAM consistently outperforms existing methods according to the proposed evaluation.

Explore similar work

Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations
Aug 12, 2026AmirHossein Eshghi, Hamid Saadatfar, Seyyed Ali Hoseini +2Etsi-Compliant Class Activation Map Explainability
How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?
May 3, 2026Daniel da Silva Costa, Pedro Nuno de Souza Moura, Adriana C. F. AlvimExplainability Saliency
Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs
Aug 3, 2026Sathiyamohan Nishankar, Nethmi Pathirana, Pubudu Sanjeewani +2Self-Supervised Vision Transformers Vision Transformer

Aug 12, 2026 · cs.CVJ/K move · Enter open · S save

Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations

AmirHossein Eshghi, Hamid Saadatfar, Seyyed Ali Hoseini, AmirMohsen Eshghi+1

Department of Computer Engineering, University of Birjand, Iran · Department of Applied Mathematics and Computer Science Visual Computing, Technical University of Denmark, Denmark

Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable artificial intelligence. Its purpose is intuitive: it converts internal model evidence into a heatmap that highlights the image regions, convolutional channels, tokens, or patches that support a target class or concept. Since the first CAM formulation in 2016, the field has moved far beyond global-average-pooled CNN classifiers. CAM-style methods now include gradient-based post-hoc explanations, gradient-free score and ablation methods, high-resolution upscaling, weakly supervised localization and segmentation, transformer token attribution, causal and debiasing methods, and foundation-model-era approaches that use CLIP, DINO, SAM, or feature-distribution comparisons. This review synthesizes a strict corpus of 57 method-centered papers published from 2016 onward. The paper develops a taxonomy that separates methods by attribution mechanism, architectural dependence, and evaluation objective. It then reviews gradient-based CAMs, recent and hybrid CAM-style methods, and model-based or architecture-aware methods. Across the corpus, the main trend is clear: the field is shifting from explaining one class score in one low-resolution CNN layer toward comparative, multi-layer, probabilistic, token-aware, and foundation-model-aware explanations. At the same time, evaluation remains fragmented. Faithfulness, localization, robustness, computational cost, and human trust are often measured with different protocols. The review therefore emphasizes not only what each method contributes, but also which gap it leaves open and which later methods attempt to close that gap.

Etsi-Compliant Class Activation Map Explainability Explainable Artificial Intelligence Convolutional Neural Networks Transformer Architectures

Open paper Ask about it PDF

Abstract

Explore similar work

Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations

How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?

Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs