Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Features
Not on the map. Why?
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 66 references that are in the map. First posted on arXiv 29 Jul 2023.
Builds on
21 of 66 references.
References · 21
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
- 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
- 2018On the Robustness of Interpretability Methodscited by 310
- 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
- 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
- 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
- 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
- 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 188
- 2017Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learningcited by 69
9 more
- 2019explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learningcited by 69
- 2018What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Playcited by 52
- 2018Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Modelscited by 50
- 2022The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizationscited by 29
- 2018The State of the Art in Integrating Machine Learning into Visual Analyticscited by 24
- 2021Automatically detecting data drift in machine learning classifierscited by 15
- 2020VisEvol: Visual Analytics to Support Hyperparameter Search through Evolutionary Optimizationcited by 9
- 2022Visualization Of Class Activation Maps To Explain AI Classification Of Network Packet Capturescited by 3
- 2021Estimation of the Global Mode of a Density: Minimaxity, Adaptation, and Computational Complexitycited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.