Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors

Zero-shot anomaly detection aims to identify defects in ar-bitrary novel domains; however, existing models assume that the auxil-iary data contains a rich diversity of anomalies, neglecting the far morecomplex and unpredictable variations in real-world target domains. Thisstudy introduces DIVE, the first approach to investigate the scenario oflimited auxiliary anomaly priors and resolve the resulting substantial per-formance degradation. Through a shallow-and-deep text embedding in-jection strategy during visual encoding, DIVE learns to abstract genericanomaly concepts shared across the auxiliary training domain and di-verse target domains. Moreover, we propose a disentanglement mech-anism to tackle the suboptimal alignment between visual embeddingsentangled with object semantics and object-agnostic textual prompts.Experiments demonstrate that, under the setting of limited anomalypatterns in auxiliary data, DIVE outperforms SOTA baselines by up to16.2% and 28.5% on two classification metrics, and 23.4%, 24.1%, and47.0% on three segmentation metrics, in terms of average performanceacross twelve datasets. Furthermore, it maintains highly competitive per-formance when auxiliary data exhibits sufficient anomaly diversity.