# Referred Object Detection on Ship Dataset SAR Imagery

Source: [Referred Object Detection on Ship Dataset SAR Imagery](<https://www.sota2.com/research/sota/referred-object-detection-on-ship-dataset-sar-imagery>)

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

Data updated: 2026-02-27T10:21:38.208Z

Evaluation of Referred Object Detection performance on the Ship Dataset SAR Imagery, reporting Mean Average Precision (mAP) broken down by object size (Small, Medium, Large) and count (Single, Multiple) at an IoU threshold of 0.5.

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 | Referred Object Detection |
| Dataset (including any stated split) | Ship Dataset SAR Imagery |
| Metric | mAP@0.5 (Small) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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@0.5 (Small)](<https://www.sota2.com/research/sota/referred-object-detection-on-ship-dataset-sar-imagery.md?metric=mAP%400.5%20(Small)>): Higher is better; unit: PERCENT.

- [mAP@0.5 (Medium)](<https://www.sota2.com/research/sota/referred-object-detection-on-ship-dataset-sar-imagery.md?metric=mAP%400.5%20(Medium)>): Higher is better; unit: PERCENT.

- [mAP@0.5 (Large)](<https://www.sota2.com/research/sota/referred-object-detection-on-ship-dataset-sar-imagery.md?metric=mAP%400.5%20(Large)>): Higher is better; unit: PERCENT.

- [mAP@0.5 (Single)](<https://www.sota2.com/research/sota/referred-object-detection-on-ship-dataset-sar-imagery.md?metric=mAP%400.5%20(Single)>): Higher is better; unit: PERCENT.

- [mAP@0.5 (Multiple)](<https://www.sota2.com/research/sota/referred-object-detection-on-ship-dataset-sar-imagery.md?metric=mAP%400.5%20(Multiple)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP@0.5 (Small) | Result date | Report paper |
| --- | --- | --- | --- |
| EarthDial | 12.14 | Not recorded | 68fa77e01e209131cea75bfc |
| GPT-4o | 0.7 | Not recorded | 68fa77e01e209131cea75bfc |

### EarthDial

mAP@0.5 (Small): 12.14. Result ID: 69a1701535dfcabb00e70609.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

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

### GPT-4o

mAP@0.5 (Small): 0.7. Result ID: 69a1701535dfcabb00e70608.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

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.
