# Open-vocabulary object detection on VAW (Visual Attributes in the Wild) (test)

Source: [Open-vocabulary object detection on VAW (Visual Attributes in the Wild) (test)](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test>)

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

Data updated: 2026-02-27T07:23:35.802Z

Evaluation of Open-Vocabulary Object Detection performance on the test split of the Visual Attributes in the Wild (VAW) dataset, reporting metrics specific to novel, known, and generalized categories.

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 | Open-vocabulary object detection |
| Dataset (including any stated split) | VAW (Visual Attributes in the Wild) (test) |
| Metric | Novel AP |
| 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

- [Novel AP](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Novel%20AP>): Higher is better; unit: PERCENT.

- [Novel AP50](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Novel%20AP50>): Higher is better; unit: PERCENT.

- [Novel AP75](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Novel%20AP75>): Higher is better; unit: PERCENT.

- [Known AP](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Known%20AP>): Higher is better; unit: PERCENT.

- [Known AP50](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Known%20AP50>): Higher is better; unit: PERCENT.

- [Known AP75](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Known%20AP75>): Higher is better; unit: PERCENT.

- [Generalized AP](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Generalized%20AP>): Higher is better; unit: PERCENT.

- [Generalized AP50](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Generalized%20AP50>): Higher is better; unit: PERCENT.

- [Generalized AP75](<https://www.sota2.com/research/sota/open-vocabulary-object-detection-on-vaw-visual-attributes-in-the-wild-test.md?metric=Generalized%20AP75>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Novel AP | Result date | Report paper |
| --- | --- | --- | --- |
| LocOv | 67 | Not recorded | 68fa6d201e209131cea37fa3 |
| OVR | 59 | Not recorded | 68fa6d201e209131cea37fa3 |
| STT-ZSD | 14 | Not recorded | 68fa6d201e209131cea37fa3 |

### LocOv

Novel AP: 67. Result ID: 69a1467535dfcabb00e5f62a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fa3.md>)

[Implementation](<https://github.com/lmb-freiburg/locov>)

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

### OVR

Novel AP: 59. Result ID: 69a1467535dfcabb00e5f629.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224aa.md>)

[Implementation](<https://github.com/alirezazareian/ovr-cnn>)

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

### STT-ZSD

Novel AP: 14. Result ID: 69a1467535dfcabb00e5f628.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fa3.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.