识别图像表示中的可解释子空间
Identifying Interpretable Subspaces in Image Representations
AI总结：
提出FALCON可解释性框架，通过对比概念解释图像表示特征，发现分组研究高阶特征可解释更大表示空间，并支持概念迁移与下游任务调试。
摘要：
我们提出了使用对比概念进行自动特征解释（FALCON），这是一个用于解释图像表示特征的可解释性框架。对于目标特征，FALCON使用大型字幕数据集（如LAION-400m）和预训练视觉-语言模型（如CLIP）为其高激活裁剪图像生成字幕。字幕中的每个单词都会被评分和排序，从而得出少量共享且人类可理解的概念，这些概念能准确描述目标特征。FALCON还利用低激活（反事实）图像进行对比解释，以消除虚假概念。尽管许多现有方法独立解释特征，但在最先进的自监督和监督模型中，我们观察到不到20%的表示空间能由单个特征解释。我们证明，较大空间中的特征在分组研究时变得更具可解释性，并可通过FALCON用高阶评分概念进行解释。我们讨论了如何利用提取的概念来解释和调试下游任务中的失败。最后，我们提出一种通过学习简单线性变换，将概念从一个（可解释的）表示空间迁移到另一个未见表示空间的技术。代码可在https://github.com/NehaKalibhat/falcon-explain获取。
英文摘要：
We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a large captioning dataset (like LAION-400m) and a pre-trained vision-language model like CLIP. Each word among the captions is scored and ranked leading to a small number of shared, human-understandable concepts that closely describe the target feature. FALCON also applies contrastive interpretation using lowly activating (counterfactual) images, to eliminate spurious concepts. Although many existing approaches interpret features independently, we observe in state-of-the-art self-supervised and supervised models, that less than 20% of the representation space can be explained by individual features. We show that features in larger spaces become more interpretable when studied in groups and can be explained with high-order scoring concepts through FALCON. We discuss how extracted concepts can be used to explain and debug failures in downstream tasks. Finally, we present a technique to transfer concepts from one (explainable) representation space to another unseen representation space by learning a simple linear transformation. Code available at https://github.com/NehaKalibhat/falcon-explain.
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。
