# Anomaly Detection on VisA to MVTec Cross-dataset (test)

Source: [Anomaly Detection on VisA to MVTec Cross-dataset (test)](<https://www.sota2.com/research/sota/anomaly-detection-on-visa-to-mvtec-cross-dataset-test>)

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

Data updated: 2026-02-26T05:47:00.890Z

Evaluation of Anomaly Detection performance using the cross-dataset test split derived from VisA and MVTec datasets.

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) | VisA to MVTec Cross-dataset (test) |
| Metric | Image-level A-AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Image-level A-AUROC](<https://www.sota2.com/research/sota/anomaly-detection-on-visa-to-mvtec-cross-dataset-test.md?metric=Image-level%20A-AUROC>): Higher is better; unit: PERCENT.

- [Pixel-level A-AUROC](<https://www.sota2.com/research/sota/anomaly-detection-on-visa-to-mvtec-cross-dataset-test.md?metric=Pixel-level%20A-AUROC>): Higher is better; unit: PERCENT.

- [Image-level FM](<https://www.sota2.com/research/sota/anomaly-detection-on-visa-to-mvtec-cross-dataset-test.md?metric=Image-level%20FM>): Higher is better; unit: PERCENT.

- [Pixel-level FM](<https://www.sota2.com/research/sota/anomaly-detection-on-visa-to-mvtec-cross-dataset-test.md?metric=Pixel-level%20FM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Image-level A-AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| CDAD | 84.2 | Not recorded | 68fa7a2c1e209131cea818cc |
| ControlNet | 78.9 | Not recorded | 68fa7a2c1e209131cea818cc |
| DIAD | 78.1 | Not recorded | 68fa7a2c1e209131cea818cc |
| IUF | 74.3 | Not recorded | 68fa7a2c1e209131cea818cc |

### CDAD

Image-level A-AUROC: 84.2. Result ID: 698b70807a967eddb76e9cb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2c1e209131cea818cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a2c1e209131cea818cc.md>)

[Implementation](<https://github.com/FuNz-0/One-for-More>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ControlNet

Image-level A-AUROC: 78.9. Result ID: 698b70807a967eddb76e9caf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2c1e209131cea818cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

Recorded evaluation configuration: {"Method category":"DM-based"}. This record does not assert independent reproduction.

### DIAD

Image-level A-AUROC: 78.1. Result ID: 698b70807a967eddb76e9cae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2c1e209131cea818cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717a1e209131cea517c4.md>)

[Implementation](<https://lewandofskee.github.io/projects/diad>)

Recorded evaluation configuration: {"Method category":"DM-based"}. This record does not assert independent reproduction.

### IUF

Image-level A-AUROC: 74.3. Result ID: 698b70807a967eddb76e9cad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2c1e209131cea818cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e71e209131cea64968.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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