ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks

2025-09-15

AI Summary

Existing concept-based interpretability methods for CNNs overlook the semantic role of individual filters and the dynamic propagation of concepts across layers. To address this, we propose ConceptFlow—a novel framework that introduces a concept transition matrix to explicitly model inter-layer concept evolution, coupled with a filter-level concept attention mechanism to hierarchically and structurally dissect the generation and propagation pathways of high-level semantic concepts. ConceptFlow integrates concept activation analysis, attention-guided reasoning, and concept path tracing to explicitly reveal the hierarchical inference logic within CNNs. Experimental results demonstrate that ConceptFlow yields explanations with strong semantic consistency and high fidelity, significantly enhancing both the depth of understanding and the granularity of interpretability for CNN decision-making processes across multiple benchmark models and datasets.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Concept-based interpretability for Convolutional Neural Networks (CNNs) aims to align internal model representations with high-level semantic concepts, but existing approaches largely overlook the semantic roles of individual filters and the dynamic propagation of concepts across layers. To address these limitations, we propose ConceptFlow, a concept-based interpretability framework that simulates the internal "thinking path" of a model by tracing how concepts emerge and evolve across layers. ConceptFlow comprises two key components: (i) concept attentions, which associate each filter with relevant high-level concepts to enable localized semantic interpretation, and (ii) conceptual pathways, derived from a concept transition matrix that quantifies how concepts propagate and transform between filters. Together, these components offer a unified and structured view of internal model reasoning. Experimental results demonstrate that ConceptFlow yields semantically meaningful insights into model reasoning, validating the effectiveness of concept attentions and conceptual pathways in explaining decision behavior. By modeling hierarchical conceptual pathways, ConceptFlow provides deeper insight into the internal logic of CNNs and supports the generation of more faithful and human-aligned explanations.

Problem

• Overlooks semantic roles of individual filters in CNNs
• Neglects dynamic concept propagation across network layers
• Lacks hierarchical view of internal model reasoning paths

Innovation

• ConceptFlow traces concept emergence across CNN layers
• Concept attentions link filters to high-level semantic concepts
• Conceptual pathways model concept propagation via transition matrix