# Horizontal Object Detection on DOTA v1.5 (test)

Source: [Horizontal Object Detection on DOTA v1.5 (test)](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test>)

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

Data updated: 2026-02-26T06:09:24.113Z

Evaluation of Horizontal Object Detection performance on the test split of the DOTA v1.5 dataset, reporting class-specific metrics (e.g., PL, BD, mAP) for aerial imagery analysis.

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 | Horizontal Object Detection |
| Dataset (including any stated split) | DOTA v1.5 (test) |
| Metric | mAP |
| 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

- [mAP](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=mAP>): Higher is better; unit: PERCENT.

- [PL](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=PL>): Higher is better; unit: PERCENT.

- [BD](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=BD>): Higher is better; unit: PERCENT.

- [BR](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=BR>): Higher is better; unit: PERCENT.

- [GTF](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=GTF>): Higher is better; unit: PERCENT.

- [SV](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=SV>): Higher is better; unit: PERCENT.

- [LV](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=LV>): Higher is better; unit: PERCENT.

- [SH](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=SH>): Higher is better; unit: PERCENT.

- [TC](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=TC>): Higher is better; unit: PERCENT.

- [BC](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=BC>): Higher is better; unit: PERCENT.

- [ST](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=ST>): Higher is better; unit: PERCENT.

- [SBF](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=SBF>): Higher is better; unit: PERCENT.

- [RA](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=RA>): Higher is better; unit: PERCENT.

- [HA](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=HA>): Higher is better; unit: PERCENT.

- [SP](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=SP>): Higher is better; unit: PERCENT.

- [HC](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=HC>): Higher is better; unit: PERCENT.

- [CC](<https://www.sota2.com/research/sota/horizontal-object-detection-on-dota-v1-5-test.md?metric=CC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP | Result date | Report paper |
| --- | --- | --- | --- |
| ReDet | 78.08 | Not recorded | 68fa697a1e209131cea2250f |
| OWSR | 77.9 | Not recorded | 68fa697a1e209131cea2250f |
| ReDet | 67.66 | Not recorded | 68fa697a1e209131cea2250f |
| Mask R-CNN | 64.54 | Not recorded | 68fa697a1e209131cea2250f |
| HTC | 64.47 | Not recorded | 68fa697a1e209131cea2250f |
| FR-O | 63.85 | Not recorded | 68fa697a1e209131cea2250f |
| RetinaNet-O | 62.49 | Not recorded | 68fa697a1e209131cea2250f |

### ReDet

mAP: 78.08. Result ID: 698dae068b517eb433231199.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Implementation](<https://github.com/csuhan/ReDet>)

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

### OWSR

mAP: 77.9. Result ID: 698dae068b517eb433231197.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

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

### ReDet

mAP: 67.66. Result ID: 698dae068b517eb433231198.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Implementation](<https://github.com/csuhan/ReDet>)

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

### Mask R-CNN

mAP: 64.54. Result ID: 698dae068b517eb433231196.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f21e209131cea01b22.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

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

### HTC

mAP: 64.47. Result ID: 698dae068b517eb433231195.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a21e209131cea0b746.md>)

[Implementation](<https://github.com/open-mmlab/mmdetection>)

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

### FR-O

mAP: 63.85. Result ID: 698dae068b517eb433231194.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62451e209131ce9f8655.md>)

[Implementation](<https://github.com/shaoqingren/faster_rcnn>)

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

### RetinaNet-O

mAP: 62.49. Result ID: 698dae068b517eb433231193.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea2250f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640c1e209131cea02556.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

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

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