Hypergraph-Enhanced Training-Free and Language-Free Few-Shot Anomaly Detection

TL;DR

HyperFSAD is a training-free, language-free few-shot anomaly detection framework that leverages hypergraph-based inference and dual-branch scoring to achieve robust, domain-agnostic performance without task-specific training.

Contribution

The paper introduces HyperFSAD, a novel approach combining hypergraph inference and dual-branch scoring, eliminating the need for training or language supervision in few-shot anomaly detection.

Findings

Achieves state-of-the-art results across six diverse datasets.

Operates effectively without task-specific training or text prompts.

Demonstrates robustness across industrial and medical domains.

Abstract

Few-shot anomaly detection (FSAD) has made significant strides, yet existing methods still face critical challenges: (i) dependence on task- or dataset-specific training/fine-tuning, (ii) reliance on language supervision or carefully hand-crafted prompts, and (iii) limited robustness across domains. In this paper, we introduce HyperFSAD, a novel FSAD framework that is training-free, language-free, and robust across domains, offering a powerful solution to these challenges. Built upon DINOv3 and a hypergraph-based inference mechanism, our approach performs inference without any task-specific optimization or text prompts, while remaining competitive. Specifically, we replace sensitive nearest-neighbor / top-$n$ matching with \textbf{Sparse Hyper Matching}: \textit{sparsemax} first selects the most relevant support patches, which are then aggregated into a \textit{hyperedge} as compact normal evidence to suppress background noise and distractors. We further introduce \textbf{Dual-Branch Image Scoring}, which fuses \emph{spatial anomaly evidence} from the patch-grid anomaly map with \emph{global semantic deviation} captured by support-aware CLS matching, yielding a robust image-level anomaly score in a strictly visual manner. Notably, all components of HyperFSAD are purely visual, eliminating the need for labor-intensive hand-crafted text prompts. Under the stringent training-free and language-free setting, HyperFSAD achieves state-of-the-art performance across six datasets spanning four industrial datasets (MVTecAD, VisA, MPDD, BTAD) and two medical datasets (RESC, BraTS).