Intrinsic Concept Extraction Based on Compositional Interpretability

2026-03-12

AI Summary

Existing unsupervised methods struggle to fully disentangle and reconstruct composable intrinsic concepts from a single image. To address this limitation, this work introduces the CI-ICE task—the first framework aimed at extracting hierarchical intrinsic concepts at both object and attribute levels. We propose HyperExpress, a novel approach that integrates diffusion generative models with hyperbolic space embeddings to achieve semantic structure-preserving and relation-aware disentangled learning in a concept-level embedding space. HyperExpress substantially outperforms current state-of-the-art methods, enabling highly interpretable and strongly compositional reconstructions from individual images.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Unsupervised Concept Extraction aims to extract concepts from a single image; however, 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.

Problem

• Unsupervised Concept Extraction
• Composable Concepts
• Intrinsic Concepts
• Concept Disentanglement
• Single Image

Innovation

• Compositional Concept Extraction
• Intrinsic Concept
• Hyperbolic Space
• Concept Disentanglement
• Diffusion Models