TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
This work addresses anomaly detection in safety-critical settings where target-domain data is unavailable, offering an incremental improvement over existing methods.
The paper tackles zero-shot anomaly detection by using a spatially aware vision-language model (TIPS) and decoupled prompts, improving image-level performance by 1.1-3.9% and pixel-level by 1.5-6.9% across seven industrial datasets.
Anomaly detection identifies departures from expected behavior in safety-critical settings. When target-domain normal data are unavailable, zero-shot anomaly detection (ZSAD) leverages vision-language models (VLMs). However, CLIP's coarse image-text alignment limits both localization and detection due to (i) spatial misalignment and (ii) weak sensitivity to fine-grained anomalies; prior work compensates with complex auxiliary modules yet largely overlooks the choice of backbone. We revisit the backbone and use TIPS-a VLM trained with spatially aware objectives. While TIPS alleviates CLIP's issues, it exposes a distributional gap between global and local features. We address this with decoupled prompts-fixed for image-level detection and learnable for pixel-level localization-and by injecting local evidence into the global score. Without CLIP-specific tricks, our TIPS-based pipeline improves image-level performance by 1.1-3.9% and pixel-level by 1.5-6.9% across seven industrial datasets, delivering strong generalization with a lean architecture. Code is available at github.com/AlirezaSalehy/Tipsomaly.