# Anomaly Segmentation on Anomaly-56K anomalous images (test)

Source: [Anomaly Segmentation on Anomaly-56K anomalous images (test)](<https://www.sota2.com/research/sota/anomaly-segmentation-on-anomaly-56k-anomalous-images-test>)

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

Data updated: 2026-04-15T08:52:33.740Z

Evaluation of Anomaly Segmentation performance on the test split of the Anomaly-56K dataset, reporting segmentation metrics like Dice, IoU, Precision, and Recall.

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 Segmentation |
| Dataset (including any stated split) | Anomaly-56K anomalous images (test) |
| Metric | Dice Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Dice Score](<https://www.sota2.com/research/sota/anomaly-segmentation-on-anomaly-56k-anomalous-images-test.md?metric=Dice%20Score>): Higher is better; unit: PERCENT.

- [IoU Score](<https://www.sota2.com/research/sota/anomaly-segmentation-on-anomaly-56k-anomalous-images-test.md?metric=IoU%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/anomaly-segmentation-on-anomaly-56k-anomalous-images-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/anomaly-segmentation-on-anomaly-56k-anomalous-images-test.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Dice Score | Result date | Report paper |
| --- | --- | --- | --- |
| IAD-Unify | 79.2 | Not recorded | 69df1b7a7d0172140ec7b83b |
| PatchCore | 30.1 | Not recorded | 69df1b7a7d0172140ec7b83b |
| STFPM | 20.8 | Not recorded | 69df1b7a7d0172140ec7b83b |
| PaDiM | 18.8 | Not recorded | 69df1b7a7d0172140ec7b83b |
| EfficientAD | 16.2 | Not recorded | 69df1b7a7d0172140ec7b83b |

### IAD-Unify

Dice Score: 79.2. Result ID: 69df50d247f34ce924c82d16.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b7a7d0172140ec7b83b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1b7a7d0172140ec7b83b.md>)

Recorded evaluation configuration: {"Model Type":"single category-agnostic region expert"}. This record does not assert independent reproduction.

### PatchCore

Dice Score: 30.1. Result ID: 69df50d247f34ce924c82d17.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b7a7d0172140ec7b83b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c751e209131cea340b9.md>)

[Implementation](<https://www.sota2.com/github.com/amazon-research/patchcore-inspection>)

Recorded evaluation configuration: {"Model Type":"per-category models"}. This record does not assert independent reproduction.

### STFPM

Dice Score: 20.8. Result ID: 69df50d247f34ce924c82d1a.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b7a7d0172140ec7b83b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c93f.md>)

Recorded evaluation configuration: {"Model Type":"per-category models"}. This record does not assert independent reproduction.

### PaDiM

Dice Score: 18.8. Result ID: 69df50d247f34ce924c82d19.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b7a7d0172140ec7b83b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c31e209131cea1e2cd.md>)

Recorded evaluation configuration: {"Model Type":"per-category models"}. This record does not assert independent reproduction.

### EfficientAD

Dice Score: 16.2. Result ID: 69df50d247f34ce924c82d18.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b7a7d0172140ec7b83b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72221e209131cea54b43.md>)

Recorded evaluation configuration: {"Model Type":"per-category models"}. This record does not assert independent reproduction.

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