基于组合可解释性的内在概念提取
Intrinsic Concept Extraction Based on Compositional Interpretability
把双曲空间的层次建模引入单图概念学习，为个性化/概念定制生成提供可组合、可解耦的概念嵌入，可直接用于少样本概念注入与属性编辑。
原文依据 leverages the inherent hierarchical modeling capability of hyperbolic space to achieve accurate concept disentanglement
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无监督概念提取旨在从单张图像中提取概念，但现有方法无法提取可组合的内在概念。为此，本文提出一项新任务，称为组合式与可解释的内在概念提取（CI-ICE）。CI-ICE 任务旨在利用基于扩散的文本到图像模型，从单张图像中提取可组合的物体级与属性级概念，使得原始概念能够通过这些概念的组合被重建。为实现这一目标，我们提出一种名为 HyperExpress 的方法，从两个核心方面解决 CI-ICE 任务。具体而言，首先，我们提出一种概念学习方法，利用双曲空间固有的层次建模能力，在保持概念间层次结构与关系依赖的同时实现准确的概念解耦；其次，我们引入一种概念级优化方法，对概念嵌入空间进行映射，在保证概念可组合性的同时维持概念间复杂的关系。我们的方法在从单张图像中提取具有组合可解释性的内在概念方面展现出卓越的性能。
英文原文摘要 1250 字符
Unsupervised Concept Extraction aims to extract concepts from a single image, yet existing methods suffer from the inability to extract composable intrinsic concepts. To address this, this paper introduces a new task called Compositional and Interpretable Intrinsic Concept Extraction (CI-ICE). The CI-ICE task aims to leverage diffusion-based text-to-image models to extract composable object-level and attribute-level concepts from a single image, such that the original concept can be reconstructed through the combination of these concepts. To achieve this goal, we propose a method called HyperExpress, which addresses the CI-ICE task through two core aspects. Specifically, first, we propose a concept learning approach that leverages the inherent hierarchical modeling capability of hyperbolic space to achieve accurate concept disentanglement while preserving the hierarchical structure and relational dependencies among concepts; second, we introduce a concept-wise optimization method that maps the concept embedding space to maintain complex inter-concept relationships while ensuring concept composability. Our method demonstrates outstanding performance in extracting compositionally interpretable intrinsic concepts from a single image.