# OOD Object Detection on Fishyscapes OoDIS (test)

Source: [OOD Object Detection on Fishyscapes OoDIS (test)](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test>)

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

Data updated: 2026-03-18T08:11:47.173Z

Evaluation of Out-of-Distribution Object Detection performance on the test split of the Fishyscapes OoDIS dataset, reporting standard object detection metrics like mAP and AR.

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 | OOD Object Detection |
| Dataset (including any stated split) | Fishyscapes OoDIS (test) |
| Metric | mAP (0.50:0.95) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [mAP (0.50:0.95)](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test.md?metric=mAP%20(0.50%3A0.95)>): Higher is better; unit: PERCENT.

- [AP50](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test.md?metric=AP50>): Higher is better; unit: PERCENT.

- [AP75](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test.md?metric=AP75>): Higher is better; unit: PERCENT.

- [AP\_S](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test.md?metric=AP_S>): Higher is better; unit: PERCENT.

- [AP\_M](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test.md?metric=AP_M>): Higher is better; unit: PERCENT.

- [AP\_L](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test.md?metric=AP_L>): Higher is better; unit: PERCENT.

- [AR@10](<https://www.sota2.com/research/sota/ood-object-detection-on-fishyscapes-oodis-test.md?metric=AR%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP (0.50:0.95) | Result date | Report paper |
| --- | --- | --- | --- |
| SynOE-OD | 33.43 | Not recorded | 69ba31ab0636e5bf4afc09b9 |
| ZS-OVODs | 22.68 | Not recorded | 69ba31ab0636e5bf4afc09b9 |
| UGainS | 15.55 | Not recorded | 69ba31ab0636e5bf4afc09b9 |

### SynOE-OD

mAP (0.50:0.95): 33.43. Result ID: 69ba5e0047f34ce924a41c40.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ab0636e5bf4afc09b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ab0636e5bf4afc09b9.md>)

Recorded evaluation configuration: {"backbone":"Swin-L"}. This record does not assert independent reproduction.

### ZS-OVODs

mAP (0.50:0.95): 22.68. Result ID: 69ba5e0047f34ce924a41c3e.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ab0636e5bf4afc09b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa748e1e209131cea62739.md>)

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

### UGainS

mAP (0.50:0.95): 15.55. Result ID: 69ba5e0047f34ce924a41c3f.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ab0636e5bf4afc09b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70371e209131cea499ca.md>)

[Implementation](<https://vision.rwth-aachen.de/ugains>)

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.