CVAILGMar 26, 2025

TraNCE: Transformative Non-linear Concept Explainer for CNNs

arXiv:2503.20230v12 citationsh-index: 3Has CodeIEEE Trans Neural Netw Learn Syst
Originality Incremental advance
AI Analysis

This work provides a more accurate and comprehensive explanation method for CNN users in computer vision, though it is incremental as it builds on existing concept-based approaches.

The paper tackles the problem of explaining CNN decisions by addressing the limitations of existing concept-based methods, which assume linear reconstructability and rely solely on fidelity for evaluation, and introduces TraNCE, a novel explainer that captures intricate activation relationships and includes a new Faith score metric, achieving improved concept discovery and visualization.

Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understanding of CNNs reveals where the models looked, concept-based explainability methods provide insights into what the models saw. However, their assumption of linear reconstructability of image activations fails to capture the intricate relationships within these activations. Their Fidelity-only approach to evaluating global explanations also presents a new concern. For the first time, we address these limitations with the novel Transformative Nonlinear Concept Explainer (TraNCE) for CNNs. Unlike linear reconstruction assumptions made by existing methods, TraNCE captures the intricate relationships within the activations. This study presents three original contributions to the CNN explainability literature: (i) An automatic concept discovery mechanism based on variational autoencoders (VAEs). This transformative concept discovery process enhances the identification of meaningful concepts from image activations. (ii) A visualization module that leverages the Bessel function to create a smooth transition between prototypical image pixels, revealing not only what the CNN saw but also what the CNN avoided, thereby mitigating the challenges of concept duplication as documented in previous works. (iii) A new metric, the Faith score, integrates both Coherence and Fidelity for a comprehensive evaluation of explainer faithfulness and consistency.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes