# Object-Level OOD Detection on STU 1.0 (test)

Source: [Object-Level OOD Detection on STU 1.0 (test)](<https://www.sota2.com/research/sota/object-level-ood-detection-on-stu-1-0-test>)

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

Data updated: 2026-04-13T09:20:08.708Z

Evaluation of Object-Level Out-of-Distribution (OOD) Detection performance on the test split of the STU 1.0 dataset, reporting object quality metrics (RecallQ, SQ, RQ, UQ, PQ).

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 | Object-Level OOD Detection |
| Dataset (including any stated split) | STU 1.0 (test) |
| Metric | RecallQ |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [RecallQ](<https://www.sota2.com/research/sota/object-level-ood-detection-on-stu-1-0-test.md?metric=RecallQ>): Higher is better; unit: PERCENT.

- [SQ](<https://www.sota2.com/research/sota/object-level-ood-detection-on-stu-1-0-test.md?metric=SQ>): Higher is better; unit: PERCENT.

- [RQ](<https://www.sota2.com/research/sota/object-level-ood-detection-on-stu-1-0-test.md?metric=RQ>): Higher is better; unit: PERCENT.

- [UQ](<https://www.sota2.com/research/sota/object-level-ood-detection-on-stu-1-0-test.md?metric=UQ>): Higher is better; unit: PERCENT.

- [PQ](<https://www.sota2.com/research/sota/object-level-ood-detection-on-stu-1-0-test.md?metric=PQ>): Higher is better; unit: PERCENT.

## Recorded results

| Method | RecallQ | Result date | Report paper |
| --- | --- | --- | --- |
| MaxLogit | 26.14 | Not recorded | 69dc78707d0172140ec789ef |
| NDP-EE | 25.58 | Not recorded | 69dc78707d0172140ec789ef |
| RbA | 24.04 | Not recorded | 69dc78707d0172140ec789ef |
| NDP-Energy | 20.31 | Not recorded | 69dc78707d0172140ec789ef |
| Void Classifier | 17.64 | Not recorded | 69dc78707d0172140ec789ef |
| Deep Ensemble | 16.75 | Not recorded | 69dc78707d0172140ec789ef |
| NDP-Entropy | 16.33 | Not recorded | 69dc78707d0172140ec789ef |
| MC Dropout | 2.25 | Not recorded | 69dc78707d0172140ec789ef |

### MaxLogit

RecallQ: 26.14. Result ID: 69dcb46647f34ce924c3e638.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c811e209131cea34603.md>)

Recorded evaluation configuration: {"Auxiliary OOD Data":"No","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

### NDP-EE

RecallQ: 25.58. Result ID: 69dcb46647f34ce924c3e63d.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

Recorded evaluation configuration: {"Auxiliary OOD Data":"Yes","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

### RbA

RecallQ: 24.04. Result ID: 69dcb46647f34ce924c3e63a.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee11e209131cea429d5.md>)

Recorded evaluation configuration: {"Auxiliary OOD Data":"No","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

### NDP-Energy

RecallQ: 20.31. Result ID: 69dcb46647f34ce924c3e63c.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

Recorded evaluation configuration: {"Auxiliary OOD Data":"Yes","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

### Void Classifier

RecallQ: 17.64. Result ID: 69dcb46647f34ce924c3e639.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

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

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

Recorded evaluation configuration: {"Auxiliary OOD Data":"Yes","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

### Deep Ensemble

RecallQ: 16.75. Result ID: 69dcb46647f34ce924c3e636.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63bc1e209131cea0084f.md>)

Recorded evaluation configuration: {"Auxiliary OOD Data":"No","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

### NDP-Entropy

RecallQ: 16.33. Result ID: 69dcb46647f34ce924c3e63b.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

Recorded evaluation configuration: {"Auxiliary OOD Data":"Yes","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

### MC Dropout

RecallQ: 2.25. Result ID: 69dcb46647f34ce924c3e637.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78707d0172140ec789ef.md>)

Recorded evaluation configuration: {"Auxiliary OOD Data":"No","Architecture":"Mask4Former \[68\]"}. This record does not assert independent reproduction.

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