# Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Features

arXiv: https://arxiv.org/abs/2308.00710 · HTML: https://mlsanity.com/paper/2308.00710/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 66 references that are in the map.
- First posted on arXiv 29 Jul 2023.

## Builds on (most cited first, 21 of 21)

- [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)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [A Survey on the Explainability of Supervised Machine Learning](https://mlsanity.com/paper/2011.07876/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Eigen-CAM: Class Activation Map using Principal Components](https://mlsanity.com/paper/2008.00299/) (2020)
- [Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learning](https://mlsanity.com/paper/1709.02656/) (2017)
- [explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning](https://mlsanity.com/paper/1908.00087/) (2019)
- [What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play](https://mlsanity.com/paper/1810.09648/) (2018)
- [Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models](https://mlsanity.com/paper/1808.00196/) (2018)
- [The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations](https://mlsanity.com/paper/2212.11737/) (2022)
- [The State of the Art in Integrating Machine Learning into Visual Analytics](https://mlsanity.com/paper/1802.07954/) (2018)
- [Automatically detecting data drift in machine learning classifiers](https://mlsanity.com/paper/2111.05672/) (2021)
- [VisEvol: Visual Analytics to Support Hyperparameter Search through Evolutionary Optimization](https://mlsanity.com/paper/2012.01205/) (2020)
- [Visualization Of Class Activation Maps To Explain AI Classification Of Network Packet Captures](https://mlsanity.com/paper/2209.02045/) (2022)
- [Estimation of the Global Mode of a Density: Minimaxity, Adaptation, and Computational Complexity](https://mlsanity.com/paper/2104.07870/) (2021)

## Built on by (most cited first, 2 of 2)

- [Interactive Analysis of Global Explanations using Aggregated Class Activation Maps for Network Data](https://mlsanity.com/paper/2608.13575/) (2026)
- [Beyond Measurement Metrics: A Human-Centered Framework for Semantic Validation of Network Traffic Classification](https://mlsanity.com/paper/2609.17014/) (2026)

## Abstract (arXiv)

Deep learning (DL) models achieve remarkable performance in classification tasks. However, models with high complexity can not be used in many risk-sensitive applications unless a comprehensible explanation is presented. Explainable artificial intelligence (xAI) focuses on the research to explain the decision-making of AI systems like DL. We extend a recent method of Class Activation Maps (CAMs) which visualizes the importance of each feature of a data sample contributing to the classification. In this paper, we aggregate CAMs from multiple samples to show a global explanation of the classification for semantically structured data. The aggregation allows the analyst to make sophisticated assumptions and analyze them with further drill-down visualizations. Our visual representation for the global CAM illustrates the impact of each feature with a square glyph containing two indicators. The color of the square indicates the classification impact of this feature. The size of the filled square describes the variability of the impact between single samples. For interesting features that require further analysis, a detailed view is necessary that provides the distribution of these values. We propose an interactive histogram to filter samples and refine the CAM to show relevant samples only. Our approach allows an analyst to detect important features of high-dimensional data and derive adjustments to the AI model based on our global explanation visualization.