UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction

2026-06-28

AI Summary

This work addresses the challenge of lacking reliable decision boundaries for unknown classes in unified visual anomaly detection by proposing a bilateral support conditional boundary construction framework. The approach integrates local matching with global relational modeling on the normal side and adaptively refines the boundary using a few abnormal samples on the anomaly side. Its key innovations include the first joint modeling of evidence from both normal and anomalous sides, introducing Optimal Transport-based Relational Modeling (OTRM), an Adaptive Coordinated Retrieval and Relational Mechanism (ACRRM), and a Few-shot Anomaly Reference (FAR) module. The method enables boundary customization without retraining and demonstrates strong performance across six datasets, achieving 84.5% image-level AUC under 1N-shot settings and improving to 85.7% with 1N+1A-shot. On MVTec-AD-SS, it attains 96.2% and 96.9% AUC at image and pixel levels, respectively.

Abstract

Unified visual anomaly detection seeks to train a single detector that can be deployed across categories, domains, and application scenarios. In the few-shot transfer regime, the key challenge is to estimate an episode-specific boundary for an unseen target category from a small support set. Existing approaches mainly infer this boundary from normal-side evidence and provide limited abnormal-side evidence for deployment-specific tolerance. Within the normal side, they often struggle to jointly capture local correspondences and global support-query relations, making their boundaries less reliable for unseen anomalies. To address these issues, we propose UniVAD v2, a two-sided support-conditioned boundary construction framework for unified visual anomaly detection. Built on the component-patch divide-and-conquer framework of UniVAD, UniVAD v2 strengthens the normal side with an Optimal Transport-based Relational Modeling module (OTRM), which complements retrieval with support-query matching through transport-style allocation, and an Adaptive Coordination mechanism for Retrieval and Relational Modeling (ACRRM), which estimates episode-conditioned reliabilities to fuse the two sources of evidence. On the abnormal side, a Few-Shot Abnormal Reference module (FAR) converts optional abnormal references into rejection-side evidence for boundary adjustment. Experiments on six datasets spanning industrial, logical, and medical anomaly detection demonstrate strong cross-domain generalization. Under the 1N-shot protocol, UniVAD v2 improves the mean image-level AUC over UniVAD from 83.0\% to 84.5\%, and further reaches 85.7\% in the 1N+1A-shot setting. On the MVTec-AD Severity Split (MVTec-AD-SS), UniVAD v2 achieves 96.2\% image-level AUC and 96.9\% pixel-level AUC, showing that abnormal references enable controllable boundary customization without retraining.

Problem

• visual anomaly detection
• few-shot learning
• support-conditioned boundary
• cross-domain generalization
• unified detection

Innovation

• Support-Conditioned Boundary
• Optimal Transport
• Few-Shot Anomaly Detection
• Unified Visual Anomaly Detection
• Abnormal Reference