FaCT: Faithful Concept Traces for Explaining Neural Network Decisions

📝 Original Info

• Title: FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
• ArXiv ID: 2510.25512
• Date: 2025-10-29
• Authors: ** 논문에 명시된 저자 정보가 제공되지 않았습니다. (필요 시 원문을 참고해 주세요.) **

📝 Abstract

Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to understand their workings, yet they are not always faithful to the model. Further, they make restrictive assumptions on the concepts a model learns, such as class-specificity, small spatial extent, or alignment to human expectations. In this work, we put emphasis on the faithfulness of such concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations. Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced. We also leverage foundation models to propose a new concept-consistency metric, C$^2$-Score, that can be used to evaluate concept-based methods. We show that, compared to prior work, our concepts are quantitatively more consistent and users find our concepts to be more interpretable, all while retaining competitive ImageNet performance.

💡 Deep Analysis

📄 Full Content

Reference