提出细粒度概念电路，精准定位模型中视觉概念的编码位置。
Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
- 通过神经元连接与语义对齐迭代发现概念电路
- 首次实现特定视觉概念的细粒度电路识别
- 适用于多种图像分类模型，提升可解释性
深度视觉模型通过分层结构实现了出色的分类性能，其中人类可理解的概念由各层神经元组合而成。由于表征具有分布式特性，精确确定特定视觉概念在模型中的编码位置仍是一项关键且具有挑战性的任务。本文提出一种有效的电路发现方法——细粒度概念电路（Granular Concept Circuit, GCC），每个电路对应一个与查询相关的视觉概念。该方法通过迭代评估神经元间的连接性，重点关注功能依赖与语义对齐，自动发现多个电路，分别捕捉查询中的特定概念。所提方法首次实现了在细粒度层面识别与特定视觉概念相关的电路，为模型提供了概念级的深刻解释。我们在多种深度图像分类模型上验证了GCC的通用性与有效性。
原文摘要 · Abstract (English)
Deep vision models have achieved remarkable classification performance by leveraging a hierarchical architecture in which human-interpretable concepts emerge through the composition of individual neurons across layers. Given the distributed nature of representations, pinpointing where specific visual concepts are encoded within a model remains a crucial yet challenging task. In this paper, we introduce an effective circuit discovery method, called Granular Concept Circuit (GCC), in which each circuit represents a concept relevant to a given query. To construct each circuit, our method iteratively assesses inter-neuron connectivity, focusing on both functional dependencies and semantic alignment. By automatically discovering multiple circuits, each capturing specific concepts within that query, our approach offers a profound, concept-wise interpretation of models and is the first to identify circuits tied to specific visual concepts at a fine-grained level. We validate the versatility and effectiveness of GCCs across various deep image classification models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。