# Anomaly Segmentation on Fishyscapes Web Oct. 2020 v1 (test)

Source: [Anomaly Segmentation on Fishyscapes Web Oct. 2020 v1 (test)](<https://www.sota2.com/research/sota/anomaly-segmentation-on-fishyscapes-web-oct-2020-v1-test>)

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

Data updated: 2026-02-26T05:22:39.780Z

Evaluation of Anomaly Segmentation performance on the test split of the Fishyscapes Web Oct. 2020 v1 dataset, measured using metrics like AP and FPR95.

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) | Fishyscapes Web Oct. 2020 v1 (test) |
| Metric | AP |
| 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

- [AP](<https://www.sota2.com/research/sota/anomaly-segmentation-on-fishyscapes-web-oct-2020-v1-test.md?metric=AP>): Higher is better; unit: PERCENT.

- [FPR95](<https://www.sota2.com/research/sota/anomaly-segmentation-on-fishyscapes-web-oct-2020-v1-test.md?metric=FPR95>): Lower is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| Outlier Head | 63.99 | Not recorded | 68fa697d1e209131cea22635 |
| Ours | 61.31 | Not recorded | 68fa697d1e209131cea22635 |
| Bayesian DeepLab | 35.8 | Not recorded | 68fa697d1e209131cea22635 |
| Dirichlet DeepLab | 30.02 | Not recorded | 68fa697d1e209131cea22635 |
| Embedding Density | 29.16 | Not recorded | 68fa697d1e209131cea22635 |
| Softmax Entropy | 16.61 | Not recorded | 68fa697d1e209131cea22635 |
| Image Resynthesis++ | 12.46 | Not recorded | 68fa697d1e209131cea22635 |

### Outlier Head

AP: 63.99. Result ID: 698daf178b517eb433231aa8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa661a1e209131cea0e4c2.md>)

Recorded evaluation configuration: {"Retrain":true}. This record does not assert independent reproduction.

### Ours

AP: 61.31. Result ID: 698daf178b517eb433231aa5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Implementation](<https://github.com/giandbt/SynBoost>)

Recorded evaluation configuration: {"Retrain":false}. This record does not assert independent reproduction.

### Bayesian DeepLab

AP: 35.8. Result ID: 698daf178b517eb433231aa6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65821e209131cea0aa5d.md>)

Recorded evaluation configuration: {"Retrain":true}. This record does not assert independent reproduction.

### Dirichlet DeepLab

AP: 30.02. Result ID: 698daf178b517eb433231aa7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088e1.md>)

Recorded evaluation configuration: {"Retrain":true}. This record does not assert independent reproduction.

### Embedding Density

AP: 29.16. Result ID: 698daf178b517eb433231aa3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ad21e209131cea2a90a.md>)

[Implementation](<https://www.sota2.com/fishyscapes.com>)

Recorded evaluation configuration: {"Retrain":false}. This record does not assert independent reproduction.

### Softmax Entropy

AP: 16.61. Result ID: 698daf178b517eb433231aa2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Retrain":false}. This record does not assert independent reproduction.

### Image Resynthesis++

AP: 12.46. Result ID: 698daf178b517eb433231aa4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22635.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa659f1e209131cea0b548.md>)

Recorded evaluation configuration: {"Retrain":false}. This record does not assert independent reproduction.

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