Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors

About

Zero-shot anomaly detection aims to identify defects in arbitrary novel domains; however, existing models assume that the auxiliary data contains a rich diversity of anomalies, neglecting the far more complex and unpredictable variations in real-world target domains. This study introduces DIVE, the first approach to investigate the scenario of limited auxiliary anomaly priors and resolve the resulting substantial performance degradation. Through a shallow-and-deep text embedding injection strategy during visual encoding, DIVE learns to abstract generic anomaly concepts shared across the auxiliary training domain and diverse target domains. Moreover, we propose a disentanglement mechanism to tackle the suboptimal alignment between visual embeddings entangled with object semantics and object-agnostic textual prompts. Experiments demonstrate that, under the setting of limited anomaly patterns in auxiliary data, DIVE outperforms SOTA baselines by up to 16.2% and 28.5% on two classification metrics, and 23.4%, 24.1%, and 47.0% on three segmentation metrics, in terms of average performance across twelve datasets. Furthermore, it maintains highly competitive performance when auxiliary data exhibits sufficient anomaly diversity.

Guanyu Lu, Fang Zhou, Cheqing Jin• 2026

Related benchmarks

TaskDatasetResultRank
Anomaly SegmentationMPDD
AUROC0.955
74
Anomaly SegmentationBTAD
Average Pixel AUROC94.3
66
SegmentationColonDB
AUROC83.2
12
SegmentationTN3K
AUROC84.1
12
SegmentationVisA
AUROC95
12
Anomaly SegmentationSDD
AUROC88.2
12
ClassificationSDD--
10
ClassificationHeadCT
AUROC99.1
6
ClassificationBr35H
AUROC96.1
6
ClassificationBrainMRI
AUROC97.3
6
Showing 10 of 26 rows

Other info

Follow for update