# Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs

arXiv: https://arxiv.org/abs/2008.02312 · HTML: https://mlsanity.com/paper/2008.02312/

## Key facts

- Cited by 151 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2020.

## Built on by (most cited first, 30 of 151)

- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [Towards Better Explanations of Class Activation Mapping](https://mlsanity.com/paper/2102.05228/) (2021)
- [Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset](https://mlsanity.com/paper/2405.18842/) (2024)
- [Character-Centric Story Visualization via Visual Planning and Token Alignment](https://mlsanity.com/paper/2210.08465/) (2022)
- [F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling](https://mlsanity.com/paper/2109.07069/) (2021)
- [Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis](https://mlsanity.com/paper/2104.10252/) (2021)
- [Learning Visual Affordance Grounding from Demonstration Videos](https://mlsanity.com/paper/2108.05675/) (2021)
- [Opti-CAM: Optimizing saliency maps for interpretability](https://mlsanity.com/paper/2301.07002/) (2023)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [Visual Explanations via Iterated Integrated Attributions](https://mlsanity.com/paper/2310.18585/) (2023)
- [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)
- [Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2209.09209/) (2022)
- [Explainable Model-Agnostic Similarity and Confidence in Face Verification](https://mlsanity.com/paper/2211.13735/) (2022)
- [TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2208.14542/) (2022)
- [Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer](https://mlsanity.com/paper/2503.14640/) (2025)
- [Re-Attention Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2208.01838/) (2022)
- [Learning Pairwise Interaction for Generalizable DeepFake Detection](https://mlsanity.com/paper/2302.13288/) (2023)
- [Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues](https://mlsanity.com/paper/2402.00281/) (2024)
- [Towards Trust of Explainable AI in Thyroid Nodule Diagnosis](https://mlsanity.com/paper/2303.04731/) (2023)
- [SketchXAI: A First Look at Explainability for Human Sketches](https://mlsanity.com/paper/2304.11744/) (2023)
- [Deep Integrated Explanations](https://mlsanity.com/paper/2310.15368/) (2023)
- [Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning](https://mlsanity.com/paper/2312.09783/) (2023)
- [Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization](https://mlsanity.com/paper/2507.10846/) (2025)
- [Negative Evidence Matters in Interpretable Histology Image Classification](https://mlsanity.com/paper/2201.02445/) (2022)
- [Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models](https://mlsanity.com/paper/2303.11969/) (2023)
- [DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2310.06196/) (2023)
- [XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach](https://mlsanity.com/paper/2407.11771/) (2024)
- [Benchmarking the Attribution Quality of Vision Models](https://mlsanity.com/paper/2407.11910/) (2024)

## Abstract (arXiv)

To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years. In particular, several Class Activation Mapping (CAM) methods have been proposed to discover the connection between CNN's decision and image regions. In spite of the reasonable visualization, lack of clear and sufficient theoretical support is the main limitation of these methods. In this paper, we introduce two axioms -- Conservation and Sensitivity -- to the visualization paradigm of the CAM methods. Meanwhile, a dedicated Axiom-based Grad-CAM (XGrad-CAM) is proposed to satisfy these axioms as much as possible. Experiments demonstrate that XGrad-CAM is an enhanced version of Grad-CAM in terms of conservation and sensitivity. It is able to achieve better visualization performance than Grad-CAM, while also be class-discriminative and easy-to-implement compared with Grad-CAM++ and Ablation-CAM. The code is available at https://github.com/Fu0511/XGrad-CAM.