Revealing Similar Semantics Inside CNNs: An Interpretable Concept-Based Comparison of Feature Spaces
Open Access
- 8 February 2025
- book chapter
- Published by Springer Nature
- p. 3-20
Abstract
Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what CNNs have learned are primarily based on performance metrics, because these allow, e.g., for cross-architecture CNN comparison. However, these neglect how knowledge is stored inside. To tackle this yet unsolved problem, our work proposes two methods for estimating the layer-wise similarity between semantic information inside CNN latent spaces. These allow insights into both the flow and likeness of semantic information within CNN layers, and into the degree of their similarity between different network architectures. As a basis, we use two renowned explainable artificial intelligence (XAI) techniques, which are used to obtain concept activation vectors, i.e., global vector representations in the latent space. These are compared with respect to their activation on test inputs. When applied to three diverse object detectors and two datasets, our methods reveal that (1) similar semantic concepts are learned regardless of the CNN architecture, and (2) similar concepts emerge in similar relative layer depth, independent of the total number of layers. Finally, our approach poses a promising step towards semantic model comparability and comprehension of how different CNNs process semantic information.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability2023
- TIDE: A General Toolbox for Identifying Object Detection Errors2020
- Explaining AI-Based Decision Support Systems Using Concept Localization Maps2020
- Expressive Explanations of DNNs by Combining Concept Analysis with ILP2020
- Concept attribution: Explaining CNN decisions to physiciansComputers in Biology and Medicine, 2020
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020
- Understanding Neural Networks via Feature Visualization: A Survey2019
- Explaining Black-Box Classifiers with ILP – Empowering LIME with Aleph to Approximate Non-linear Decisions with Relational Rules2018
- SSD: Single Shot MultiBox Detector2016
- Microsoft COCO: Common Objects in Context2014