# Towards Better Explanations of Class Activation Mapping

arXiv: https://arxiv.org/abs/2102.05228 · HTML: https://mlsanity.com/paper/2102.05228/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 10 Feb 2021.

## Builds on (most cited first, 16 of 16)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (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)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [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)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs](https://mlsanity.com/paper/2008.02312/) (2020)

## Built on by (most cited first, 30 of 47)

- [Gradient based Feature Attribution in Explainable AI: A Technical Review](https://mlsanity.com/paper/2403.10415/) (2024)
- [Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach](https://mlsanity.com/paper/2309.07944/) (2023)
- [Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions](https://mlsanity.com/paper/2306.05731/) (2023)
- [Visual Explanations via Iterated Integrated Attributions](https://mlsanity.com/paper/2310.18585/) (2023)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)
- [Saliency Cards: A Framework to Characterize and Compare Saliency Methods](https://mlsanity.com/paper/2206.02958/) (2022)
- [Deep Integrated Explanations](https://mlsanity.com/paper/2310.15368/) (2023)
- [PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference](https://mlsanity.com/paper/2403.16020/) (2024)
- [A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future](https://mlsanity.com/paper/2412.14056/) (2024)
- [FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs](https://mlsanity.com/paper/2206.08792/) (2022)
- [NAISR: A 3D Neural Additive Model for Interpretable Shape Representation](https://mlsanity.com/paper/2303.09234/) (2023)
- [Rethinking Explainability in the Era of Multimodal AI](https://mlsanity.com/paper/2506.13060/) (2025)
- [Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations](https://mlsanity.com/paper/2303.09171/) (2023)
- [CAMs as Shapley Value-based Explainers](https://mlsanity.com/paper/2501.06261/) (2025)
- [Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Models](https://mlsanity.com/paper/2310.16584/) (2023)
- [CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation](https://mlsanity.com/paper/2404.02388/) (2024)
- [Explaining Object Detectors via Collective Contribution of Pixels](https://mlsanity.com/paper/2412.00666/) (2024)
- [Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentation](https://mlsanity.com/paper/2310.01828/) (2023)
- [Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models](https://mlsanity.com/paper/2412.01202/) (2024)
- [Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification](https://mlsanity.com/paper/2307.05017/) (2023)
- [Overview of Class Activation Maps for Visualization Explainability](https://mlsanity.com/paper/2309.14304/) (2023)
- [Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information](https://mlsanity.com/paper/2405.04913/) (2024)
- [Leveraging CAM Algorithms for Explaining Medical Semantic Segmentation](https://mlsanity.com/paper/2409.20287/) (2024)
- [Region-Aware CAM: High-Resolution Weakly-Supervised Defect Segmentation via Salient Region Perception](https://mlsanity.com/paper/2506.22866/) (2025)
- [Understanding CNNs from excitations](https://mlsanity.com/paper/2205.00932/) (2022)
- [Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study](https://mlsanity.com/paper/2205.06546/) (2022)
- [Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium](https://mlsanity.com/paper/2205.11109/) (2022)
- [Towards a Praxis for Intercultural Ethics in Explainable AI](https://mlsanity.com/paper/2304.11861/) (2023)
- [Rethinking Class Activation Maps for Segmentation: Revealing Semantic Information in Shallow Layers by Reducing Noise](https://mlsanity.com/paper/2308.02118/) (2023)
- [Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance](https://mlsanity.com/paper/2312.14201/) (2023)

## Abstract (arXiv)

Increasing demands for understanding the internal behavior of convolutional neural networks (CNNs) have led to remarkable improvements in explanation methods. Particularly, several class activation mapping (CAM) based methods, which generate visual explanation maps by a linear combination of activation maps from CNNs, have been proposed. However, the majority of the methods lack a clear theoretical basis on how they assign the coefficients of the linear combination. In this paper, we revisit the intrinsic linearity of CAM with respect to the activation maps; we construct an explanation model of CNN as a linear function of binary variables that denote the existence of the corresponding activation maps. With this approach, the explanation model can be determined by additive feature attribution methods in an analytic manner. We then demonstrate the adequacy of SHAP values, which is a unique solution for the explanation model with a set of desirable properties, as the coefficients of CAM. Since the exact SHAP values are unattainable, we introduce an efficient approximation method, LIFT-CAM, based on DeepLIFT. Our proposed LIFT-CAM can estimate the SHAP values of the activation maps with high speed and accuracy. Furthermore, it greatly outperforms other previous CAM-based methods in both qualitative and quantitative aspects.