用感知组件解释表征学习
Explaining Representation Learning with Perceptual Components
AI总结：
针对自监督表征语义不明、传统解释方法失效的问题，提出通过选择性遮蔽颜色、形状和纹理生成重要性图，以无标签且符合人类视觉的方式解释不同训练目标与图像域下的表征。
摘要：
自监督模型所创建的表征空间缺乏清晰的语义含义。表征的这一可解释性问题使传统可解释性方法在此情境下失效。本文提出一种利用颜色、形状和纹理三个关键感知组件分析表征空间的新方法。我们采用对这些组件进行选择性遮蔽的方式来观察表征的变化，从而为每个组件生成不同的重要性图。在缺少标签的场景中，这些重要性图提供了更直观的解释，因为它们是人类视觉系统不可或缺的组成部分。我们的方法增强了表征空间的可解释性，所提供的解释能够与人类视觉感知产生共鸣。我们利用感知组件分析了不同训练目标如何创建不同的表征空间。此外，我们还考察了图像在多种图像域中的表征，从而深入理解这些组件在不同情境中的作用。
英文摘要：
Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods ineffective in this context. In this paper, we introduce a novel method to analyze representation spaces using three key perceptual components: color, shape, and texture. We employ selective masking of these components to observe changes in representations, resulting in distinct importance maps for each. In scenarios, where labels are absent, these importance maps provide more intuitive explanations as they are integral to the human visual system. Our approach enhances the interpretability of the representation space, offering explanations that resonate with human visual perception. We analyze how different training objectives create distinct representation spaces using perceptual components. Additionally, we examine the representation of images across diverse image domains, providing insights into the role of these components in different contexts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
