# Anomaly Detection on Industrial and Medical Datasets Average

Source: [Anomaly Detection on Industrial and Medical Datasets Average](<https://www.sota2.com/research/sota/anomaly-detection-on-industrial-and-medical-datasets-average>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T08:20:51.961Z

Evaluation of Anomaly Detection performance averaged across a collection of industrial and medical datasets, reporting metrics like I-AUROC and I-AP.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Anomaly Detection |
| Dataset (including any stated split) | Industrial and Medical Datasets Average |
| Metric | I-AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [I-AUROC](<https://www.sota2.com/research/sota/anomaly-detection-on-industrial-and-medical-datasets-average.md?metric=I-AUROC>): Higher is better; unit: PERCENT.

- [I-AP](<https://www.sota2.com/research/sota/anomaly-detection-on-industrial-and-medical-datasets-average.md?metric=I-AP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | I-AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| CoPS | 92.5 | Not recorded | 68fa7a641e209131cea82d85 |
| FAPrompt | 91.1 | Not recorded | 68fa7a641e209131cea82d85 |
| AdaCLIP | 90 | Not recorded | 68fa7a641e209131cea82d85 |
| AnomalyCLIP | 90 | Not recorded | 68fa7a641e209131cea82d85 |
| CLIP-AD | 87.6 | Not recorded | 68fa7a641e209131cea82d85 |
| APRIL-GAN | 83.9 | Not recorded | 68fa7a641e209131cea82d85 |
| WinCLIP | 83.2 | Not recorded | 68fa7a641e209131cea82d85 |

### CoPS

I-AUROC: 92.5. Result ID: 69ddf8c447f34ce924c5530f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

Recorded evaluation configuration: {"Prompting Category":"Prompt Learning","Backbone":"CLIP (ViT-L/14@336px)","Resolution":"518 x 518","Setting":"Zero-Shot Anomaly Detection"}. This record does not assert independent reproduction.

### FAPrompt

I-AUROC: 91.1. Result ID: 69ddf8c447f34ce924c5530e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd61e209131cea8ad50.md>)

Recorded evaluation configuration: {"Prompting Category":"Prompt Learning","Backbone":"CLIP (ViT-L/14@336px)","Resolution":"518 x 518","Setting":"Zero-Shot Anomaly Detection"}. This record does not assert independent reproduction.

### AdaCLIP

I-AUROC: 90. Result ID: 69ddf8c447f34ce924c5530c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea708e2.md>)

[Implementation](<https://github.com/caoyunkang/AdaCLIP>)

Recorded evaluation configuration: {"Prompting Category":"Prompt Design","Backbone":"CLIP (ViT-L/14@336px)","Resolution":"518 x 518","Setting":"Zero-Shot Anomaly Detection"}. This record does not assert independent reproduction.

### AnomalyCLIP

I-AUROC: 90. Result ID: 69ddf8c447f34ce924c5530d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78451e209131cea77851.md>)

[Implementation](<https://github.com/zqhang/AnomalyCLIP>)

Recorded evaluation configuration: {"Prompting Category":"Prompt Learning","Backbone":"CLIP (ViT-L/14@336px)","Resolution":"518 x 518","Setting":"Zero-Shot Anomaly Detection"}. This record does not assert independent reproduction.

### CLIP-AD

I-AUROC: 87.6. Result ID: 69ddf8c447f34ce924c5530b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72641e209131cea562a8.md>)

Recorded evaluation configuration: {"Prompting Category":"Prompt Design","Backbone":"CLIP (ViT-L/14@336px)","Resolution":"518 x 518","Setting":"Zero-Shot Anomaly Detection"}. This record does not assert independent reproduction.

### APRIL-GAN

I-AUROC: 83.9. Result ID: 69ddf8c447f34ce924c5530a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95d.md>)

[Implementation](<https://github.com/ByChelsea/VAND-APRIL-GAN>)

Recorded evaluation configuration: {"Prompting Category":"Prompt Design","Backbone":"CLIP (ViT-L/14@336px)","Resolution":"518 x 518","Setting":"Zero-Shot Anomaly Detection"}. This record does not assert independent reproduction.

### WinCLIP

I-AUROC: 83.2. Result ID: 69ddf8c447f34ce924c55309.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e2d.md>)

Recorded evaluation configuration: {"Prompting Category":"Prompt Design","Backbone":"CLIP (ViT-L/14@336px)","Resolution":"518 x 518","Setting":"Zero-Shot Anomaly Detection"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
