Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory

2025-11-08

AI Summary

To address the scarcity of training samples and the challenge of covering diverse test distributions in few-shot multimodal industrial anomaly detection, this paper proposes a hypergraph-enhanced memory mechanism. Methodologically, it introduces high-order relational modeling to this task for the first time: a hypergraph captures structural commonalities among limited normal samples to construct an intra-class structural prior memory bank; a training-free hypergraph message-passing mechanism coupled with hyperedge-guided memory retrieval enables semantic-aware memory updating and efficient matching; and multimodal feature fusion enhances representation robustness. Evaluated on MVTec 3D-AD and Eyecandies, the method significantly outperforms existing state-of-the-art approaches—reducing false positive rate by 12.6% while substantially improving detection accuracy and cross-scenario generalization capability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Few-shot multimodal industrial anomaly detection is a critical yet underexplored task, offering the ability to quickly adapt to complex industrial scenarios. In few-shot settings, insufficient training samples often fail to cover the diverse patterns present in test samples. This challenge can be mitigated by extracting structural commonality from a small number of training samples. In this paper, we propose a novel few-shot unsupervised multimodal industrial anomaly detection method based on structural commonality, CIF (Commonality In Few). To extract intra-class structural information, we employ hypergraphs, which are capable of modeling higher-order correlations, to capture the structural commonality within training samples, and use a memory bank to store this intra-class structural prior. Firstly, we design a semantic-aware hypergraph construction module tailored for single-semantic industrial images, from which we extract common structures to guide the construction of the memory bank. Secondly, we use a training-free hypergraph message passing module to update the visual features of test samples, reducing the distribution gap between test features and features in the memory bank. We further propose a hyperedge-guided memory search module, which utilizes structural information to assist the memory search process and reduce the false positive rate. Experimental results on the MVTec 3D-AD dataset and the Eyecandies dataset show that our method outperforms the state-of-the-art (SOTA) methods in few-shot settings. Code is available at https://github.com/Sunny5250/CIF.

Problem

• Detects industrial anomalies using few-shot multimodal data
• Extracts structural commonality from limited training samples
• Reduces false positives through hypergraph-enhanced memory search

Innovation

• Hypergraphs model higher-order correlations for structural commonality
• Memory bank stores intra-class structural prior information
• Training-free hypergraph message passing updates test features