Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
It provides a single, generalizable solution for image clustering across varied scenarios, eliminating the need for task-specific training.
The paper introduces a universal framework for image clustering that uses textual guidelines to bridge gaps across different clustering scenarios, outperforming specialized methods on diverse tasks.
Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image Clustering Agent, the first universal framework that bridges these gaps through textual guidelines. To incorporate complex guidelines without task-specific training, we propose Generative Concept Proxy Modeling, which generates guideline-aware embeddings via concept proxy extraction. For scenarios requiring automatic cluster discovery, we introduce LLM Traversal based on Minimum Spanning Tree that selectively applies LLM reasoning for complex semantic judgments. Our method generalizes across diverse clustering scenarios spanning from general to fine-grained categorization, from global to local criteria, and from balanced to long-tail distributions. Our framework consistently outperforms specialized methods across diverse clustering tasks.