Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Heterogeneous Hypergraph Vision-Language Reasoning (H2VLR), a novel framework for few-shot anomaly detection that leverages Vision-Language Models (VLMs). H2VLR addresses the limitations of pairwise feature matching in existing VLM-based approaches by modeling visual regions and semantic concepts within a unified hypergraph, enabling high-order inference of visual-semantic relations. Experiments on industrial and medical benchmarks demonstrate that H2VLR achieves state-of-the-art performance in few-shot anomaly detection scenarios.
Forget simple feature matching: modeling visual-semantic relations with hypergraphs unlocks state-of-the-art few-shot anomaly detection.
As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a frequently-faced issue. To solve it, the few-shot anomaly detection (FSAD) scheme is attracting increasing attention. In recent years, beyond traditional visual paradigm, Vision-Language Model (VLM) has been extensively explored to boost this field. However, in currently-existing VLM-based FSAD schemes, almost all perform anomaly inference only by pairwise feature matching, ignoring structural dependencies and global consistency. To further redound to FSAD via VLM, we propose a Heterogeneous Hypergraph Vision-Language Reasoning (H2VLR) framework. It reformulates the FSAD as a high-order inference problem of visual-semantic relations, by jointly modeling visual regions and semantic concepts in a unified hypergraph. Experimental comparisons verify the effectiveness and advantages of H2VLR. It could often achieve state-of-the-art (SOTA) performance on representative industrial and medical benchmarks. Our code will be released upon acceptance.