4 papers
XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection
Mingxiu Cai, Zhe Zhang, Gaochang Wu +1
The remarkable success of reconstruction-based methods in Unsupervised Anomaly Detection (UAD) lies in their ability to identify and localize anomalies by modeling discrepancies be…
RAID: Retrieval-Augmented Anomaly Detection
Mingxiu Cai, Zhe Zhang, Gaochang Wu +2
Unsupervised Anomaly Detection (UAD) aims to identify abnormal regions by establishing correspondences between test images and normal templates. Existing methods primarily rely on…
Unified Unsupervised Anomaly Detection via Matching Cost Filtering
Zhe Zhang, Mingxiu Cai, Gaochang Wu +5
Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data, with wide applications such as industrial inspection and med…
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
Zhe Zhang, Mingxiu Cai, Hanxiao Wang +3
Unsupervised anomaly detection (UAD) seeks to localize the anomaly mask of an input image with respect to normal samples. Either by reconstructing normal counterparts (reconstructi…