# Oriented Object Detection on DOTA v2.0 (val)

Source: [Oriented Object Detection on DOTA v2.0 (val)](<https://www.sota2.com/research/sota/oriented-object-detection-on-dota-v2-0-val>)

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

Data updated: 2026-03-04T17:58:59.660Z

Evaluation of Oriented Object Detection performance on the validation split of the DOTA v2.0 dataset, reporting mAP metrics at IoU thresholds of 10%, 20%, and 30%.

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 | Oriented Object Detection |
| Dataset (including any stated split) | DOTA v2.0 (val) |
| Metric | mAP (10%) |
| 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

- [mAP (10%)](<https://www.sota2.com/research/sota/oriented-object-detection-on-dota-v2-0-val.md?metric=mAP%20(10%25)>): Higher is better; unit: PERCENT.

- [mAP (20%)](<https://www.sota2.com/research/sota/oriented-object-detection-on-dota-v2-0-val.md?metric=mAP%20(20%25)>): Higher is better; unit: PERCENT.

- [mAP (30%)](<https://www.sota2.com/research/sota/oriented-object-detection-on-dota-v2-0-val.md?metric=mAP%20(30%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP (10%) | Result date | Report paper |
| --- | --- | --- | --- |
| PWOOD | 31.03 | Not recorded | 68fa79d71e209131cea7faa5 |
| Vanilla Baseline | 24.77 | Not recorded | 68fa79d71e209131cea7faa5 |
| H2RBox-v2 | 19.07 | Not recorded | 68fa79d71e209131cea7faa5 |
| PWOOD | 13.44 | Not recorded | 68fa79d71e209131cea7faa5 |
| Point2RBox-v2 | 12.18 | Not recorded | 68fa79d71e209131cea7faa5 |

### PWOOD

mAP (10%): 31.03. Result ID: 69a872d16dbb7075b9507168.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7faa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7faa5.md>)

Recorded evaluation configuration: {"Annotation":"Partial HBox Annotations"}. This record does not assert independent reproduction.

### Vanilla Baseline

mAP (10%): 24.77. Result ID: 69a872d16dbb7075b9507167.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7faa5.md>)

Recorded evaluation configuration: {"Task":"SOOD","Annotation":"Partial RBox"}. This record does not assert independent reproduction.

### H2RBox-v2

mAP (10%): 19.07. Result ID: 69a872d16dbb7075b9507165.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7faa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ee1e209131cea4e1fb.md>)

Recorded evaluation configuration: {"Task":"WOOD"}. This record does not assert independent reproduction.

### PWOOD

mAP (10%): 13.44. Result ID: 69a872d16dbb7075b9507169.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7faa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7faa5.md>)

Recorded evaluation configuration: {"Annotation":"Partial Point Annotations"}. This record does not assert independent reproduction.

### Point2RBox-v2

mAP (10%): 12.18. Result ID: 69a872d16dbb7075b9507166.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d71e209131cea7faa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76e71e209131cea6fd23.md>)

[Implementation](<https://github.com/VisionXLab/point2rbox-v2>)

Recorded evaluation configuration: {"Task":"WOOD"}. This record does not assert independent reproduction.

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