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

arXiv: https://arxiv.org/abs/2608.12299 · HTML: https://mlsanity.com/paper/2608.12299/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 55 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Builds on (most cited first, 30 of 31)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2004.04581/) (2020)
- [Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization](https://mlsanity.com/paper/1704.04232/) (2017)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.08896/) (2021)
- [Attention-based Dropout Layer for Weakly Supervised Object Localization](https://mlsanity.com/paper/1908.10028/) (2019)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [Self-produced Guidance for Weakly-supervised Object Localization](https://mlsanity.com/paper/1807.08902/) (2018)
- [Towards Better Explanations of Class Activation Mapping](https://mlsanity.com/paper/2102.05228/) (2021)
- [Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2110.05741/) (2021)
- [Extracting Class Activation Maps from Non-Discriminative Features as well](https://mlsanity.com/paper/2303.10334/) (2023)
- [F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling](https://mlsanity.com/paper/2109.07069/) (2021)
- [TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.07239/) (2022)
- [CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping](https://mlsanity.com/paper/2205.13922/) (2022)
- [Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks](https://mlsanity.com/paper/2207.03648/) (2022)
- [Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring](https://mlsanity.com/paper/2102.07805/) (2021)
- [Keep CALM and Improve Visual Feature Attribution](https://mlsanity.com/paper/2106.07861/) (2021)
- [Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation](https://mlsanity.com/paper/2501.11309/) (2025)
- [Improving Weakly-supervised Object Localization via Causal Intervention](https://mlsanity.com/paper/2104.10351/) (2021)
- [Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis](https://mlsanity.com/paper/2501.09333/) (2025)
- [Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning](https://mlsanity.com/paper/2012.05567/) (2020)
- [Poly-CAM: High resolution class activation map for convolutional neural networks](https://mlsanity.com/paper/2204.13359/) (2022)
- [CAMs as Shapley Value-based Explainers](https://mlsanity.com/paper/2501.06261/) (2025)
- [CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation](https://mlsanity.com/paper/2404.02388/) (2024)

## Abstract (arXiv)

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.