# Oriented Object Detection on SAT-MTB Official

Source: [Oriented Object Detection on SAT-MTB Official](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official>)

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

Data updated: 2026-06-16T07:29:18.400Z

Evaluation of Oriented Object Detection performance on the SAT-MTB Official dataset, reporting metrics including mAP and various orientation-specific scores (CA, CS, FA, etc.).

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) | SAT-MTB Official |
| Metric | CA |
| 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

- [CA](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=CA>): Higher is better; unit: PERCENT.

- [CS](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=CS>): Higher is better; unit: PERCENT.

- [FA](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=FA>): Higher is better; unit: PERCENT.

- [FH](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=FH>): Higher is better; unit: PERCENT.

- [NA](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=NA>): Higher is better; unit: PERCENT.

- [NV](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=NV>): Higher is better; unit: PERCENT.

- [OS](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=OS>): Higher is better; unit: PERCENT.

- [RA](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=RA>): Higher is better; unit: PERCENT.

- [SB](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=SB>): Higher is better; unit: PERCENT.

- [TN](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=TN>): Higher is better; unit: PERCENT.

- [WA](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=WA>): Higher is better; unit: PERCENT.

- [YC](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=YC>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/oriented-object-detection-on-sat-mtb-official.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CA | Result date | Report paper |
| --- | --- | --- | --- |
| ReDet | 81.1 | Not recorded | 6a30d86fd33dfb23e783cb0e |
| RetinaNet-OBB | 51.9 | Not recorded | 6a30d86fd33dfb23e783cb0e |
| FCOS-OBB | 42.6 | Not recorded | 6a30d86fd33dfb23e783cb0e |
| Oriented RCNN | 42.2 | Not recorded | 6a30d86fd33dfb23e783cb0e |
| RoI Transformer | 38.2 | Not recorded | 6a30d86fd33dfb23e783cb0e |
| Faster RCNN-OBB | 20.7 | Not recorded | 6a30d86fd33dfb23e783cb0e |
| R3Det | 20.7 | Not recorded | 6a30d86fd33dfb23e783cb0e |
| S2ANet | 19.1 | Not recorded | 6a30d86fd33dfb23e783cb0e |

### ReDet

CA: 81.1. Result ID: 6a30fb18fbc373592c2cd301.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

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

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

Recorded evaluation configuration: {"Accepted By":"CVPR2021","Backbone":"ReResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

### RetinaNet-OBB

CA: 51.9. Result ID: 6a30fb18fbc373592c2cd2fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

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

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

Recorded evaluation configuration: {"Accepted By":"ICCV2017","Backbone":"ResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

### FCOS-OBB

CA: 42.6. Result ID: 6a30fb18fbc373592c2cd2fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66361e209131cea0ed2a.md>)

[Implementation](<https://www.sota2.com/tinyurl.com/FCOSv1>)

Recorded evaluation configuration: {"Accepted By":"ICCV2019","Backbone":"ResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

### Oriented RCNN

CA: 42.2. Result ID: 6a30fb18fbc373592c2cd2fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a921e209131cea28f30.md>)

[Implementation](<https://github.com/jbwang1997/OBBDetection>)

Recorded evaluation configuration: {"Accepted By":"ICCV2021","Backbone":"ResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

### RoI Transformer

CA: 38.2. Result ID: 6a30fb18fbc373592c2cd2fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

Recorded evaluation configuration: {"Accepted By":"CVPR2018","Backbone":"ResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

### Faster RCNN-OBB

CA: 20.7. Result ID: 6a30fb18fbc373592c2cd2fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

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

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

Recorded evaluation configuration: {"Accepted By":"IEEE2017","Backbone":"ResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

### R3Det

CA: 20.7. Result ID: 6a30fb18fbc373592c2cd2ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

Recorded evaluation configuration: {"Accepted By":"AAAI2021","Backbone":"ResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

### S2ANet

CA: 19.1. Result ID: 6a30fb18fbc373592c2cd300.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d86fd33dfb23e783cb0e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a531e209131cea275da.md>)

[Implementation](<https://github.com/csuhan/s2anet>)

Recorded evaluation configuration: {"Accepted By":"TGRS2021","Backbone":"ResNet50","Training Images":"26155","Size":"1024","Epoch":"12"}. This record does not assert independent reproduction.

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