TU Darmstadt / ULB / TUbiblio

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

Cherepanov, Igor ; Sessler, David ; Ulmer, Alex ; Lücke-Tieke, Hendrik ; Kohlhammer, Jörn (2023)
Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Features.
1st World Conference on eXplainable Artificial Intelligence (xAI 2023). Lisbon, Portugal (26.-28.07.2023)
doi: 10.1007/978-3-031-44067-0_1
Conference or Workshop Item, Bibliographie

Abstract

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.

Item Type: Conference or Workshop Item
Erschienen: 2023
Creators: Cherepanov, Igor ; Sessler, David ; Ulmer, Alex ; Lücke-Tieke, Hendrik ; Kohlhammer, Jörn
Type of entry: Bibliographie
Title: Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Features
Language: English
Date: 21 October 2023
Publisher: Springer
Book Title: Explainable Artificial Intelligence
Series: Communications in Computer and Information Science
Series Volume: 1902
Event Title: 1st World Conference on eXplainable Artificial Intelligence (xAI 2023)
Event Location: Lisbon, Portugal
Event Dates: 26.-28.07.2023
DOI: 10.1007/978-3-031-44067-0_1
Abstract:

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.

Uncontrolled Keywords: Machine learning, Interactive machine learning
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Date Deposited: 08 Nov 2023 13:27
Last Modified: 08 Nov 2023 13:27
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details