Personalizing Vision-Language Models With Hybrid Prompts for Zero-Shot Anomaly Detection
Bibliographic record
Abstract
Zero-shot anomaly detection (ZSAD) aims to develop a foundational model capable of detecting anomalies across arbitrary categories without relying on reference images. However, since "abnormality" is inherently defined in relation to "normality" within specific categories, detecting anomalies without reference images describing the corresponding normal context remains a significant challenge. As an alternative to reference images, this study explores the use of widely available product standards to characterize normal contexts and potential abnormal states. Specifically, this study introduces AnomalyVLM, which leverages generalized pretrained vision-language models (VLMs) to interpret these standards and detect anomalies. Given the current limitations of VLMs in comprehending complex textual information, AnomalyVLM generates hybrid prompts-comprising prompts for abnormal regions, symbolic rules, and region numbers-from the standards to facilitate more effective understanding. These hybrid prompts are incorporated into various stages of the anomaly detection process within the selected VLMs, including an anomaly region generator and an anomaly region refiner. By utilizing hybrid prompts, VLMs are personalized as anomaly detectors for specific categories, offering users flexibility and control in detecting anomalies across novel categories without the need for training data. Experimental results on four public industrial anomaly detection datasets, as well as a practical automotive part inspection task, highlight the superior performance and enhanced generalization capability of AnomalyVLM, especially in texture categories. An online demo of AnomalyVLM is available at https://github.com/caoyunkang/Segment-Any-Anomaly.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".