ConEx：通过概念感知归因实现人类可解释的显著性图
ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
浏览论文内容
中文总结 AI 辅助
ConEx提出了一种结合显著性可视化与概念推理的框架，通过自动发现概念激活向量生成忠实且可解释的显著性图，并引入VCM和CCM指标，在多个基准上达到最先进性能。
中文摘要 AI 辅助
计算机视觉中的许多视觉解释方法强调像素重要性，但难以将这些低级线索与语义上有意义的概念联系起来，限制了其可解释性和可信度。我们提出了基于概念的解释（ConEx），这是一种新颖的框架，将显著性可视化与基于概念的推理相结合，以提供忠实性和可解释性。ConEx自动发现类别特定的概念，并通过概念激活向量（CAVs）表示它们，这些向量无需人工监督即可学习，利用一种架构特定的掩蔽机制来减少分割掩码引入的噪声，从而增强概念的纯净度。ConEx生成忠实的显著性图，揭示每个概念在图像中的出现位置及其对预测的贡献。为了评估这些学习到的概念的可靠性，我们提出了两个互补的指标：向量-概念匹配（VCM）和概念-类别匹配（CCM），它们量化概念对齐，并允许与现有方法进行直接比较。在多种设置下的大量实验表明，ConEx在忠实性、分割和概念质量基准上达到了最先进的性能。总体而言，ConEx推动了视觉模型向真正可解释且基于概念的解释领域的发展。
英文摘要
Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting their interpretability and trustworthiness. We introduce Concept-based Explanations (ConEx), a novel framework that bridges saliency visualization with concept-based reasoning to provide both faithfulness and interpretability. ConEx automatically discovers class-specific concepts and represents them through concept activation vectors (CAVs), learned without manual supervision using an architecture-specific masking mechanism that reduces noise introduced by the segmentation masks to enhance concept purity. ConEx generates faithful saliency maps that reveal where each concept appears in the image and how it contributes to the prediction. To evaluate the reliability of these learned concepts, we propose two complementary metrics, Vector-Concept Match (VCM) and Concept-Class Match (CCM), that quantify concept alignment and enable direct comparison with existing methods. Extensive experiments across diverse settings demonstrate that ConEx achieves state-of-the-art performance on faithfulness, segmentation, and concept-quality benchmarks. Overall, ConEx advances the field toward truly interpretable and concept-grounded explanations in vision models.
发表机构
- Tel Aviv University（特拉维夫大学）
- The Open University（开放大学）
机构由 AI 辅助整理，请以论文原文为准。
