# Object Detection on In-House Dataset #1

Source: [Object Detection on In-House Dataset #1](<https://www.sota2.com/research/sota/object-detection-on-in-house-dataset-sharp-1>)

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

Data updated: 2026-03-16T09:16:04.939Z

Evaluation of Object Detection performance on the proprietary In-House Dataset #1.

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 | Object Detection |
| Dataset (including any stated split) | In-House Dataset #1 |
| Metric | mAP (0.5:0.95) |
| 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 (0.5:0.95)](<https://www.sota2.com/research/sota/object-detection-on-in-house-dataset-sharp-1.md?metric=mAP%20(0.5%3A0.95)>): Higher is better; unit: PERCENT.

- [mAR (IoU=1.0)](<https://www.sota2.com/research/sota/object-detection-on-in-house-dataset-sharp-1.md?metric=mAR%20(IoU%3D1.0)>): Higher is better; unit: PERCENT.

- [F1 Score (0.5:0.95)](<https://www.sota2.com/research/sota/object-detection-on-in-house-dataset-sharp-1.md?metric=F1%20Score%20(0.5%3A0.95)>): Higher is better; unit: PERCENT.

- [Precision (0.5:0.95)](<https://www.sota2.com/research/sota/object-detection-on-in-house-dataset-sharp-1.md?metric=Precision%20(0.5%3A0.95)>): Higher is better; unit: PERCENT.

- [Recall (0.5:0.95)](<https://www.sota2.com/research/sota/object-detection-on-in-house-dataset-sharp-1.md?metric=Recall%20(0.5%3A0.95)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP (0.5:0.95) | Result date | Report paper |
| --- | --- | --- | --- |
| MOD | 10 | Not recorded | 69b78e670636e5bf4afbdaa3 |
| RexOmni | 6 | Not recorded | 69b78e670636e5bf4afbdaa3 |
| RexOmni | 4 | Not recorded | 69b78e670636e5bf4afbdaa3 |
| GroundingDINO | 4 | Not recorded | 69b78e670636e5bf4afbdaa3 |
| YoloWorld | 2 | Not recorded | 69b78e670636e5bf4afbdaa3 |
| GroundingDINO | 0 | Not recorded | 69b78e670636e5bf4afbdaa3 |
| YoloWorld | 0 | Not recorded | 69b78e670636e5bf4afbdaa3 |

### MOD

mAP (0.5:0.95): 10. Result ID: 69b7ca3a47f34ce9249fb055.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

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

### RexOmni

mAP (0.5:0.95): 6. Result ID: 69b7ca3a47f34ce9249fb04f.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1c1e209131cea8c69b.md>)

[Implementation](<https://github.com/IDEA-Research/Rex-Omni>)

Recorded evaluation configuration: {"Prompt":"GPT-Prompt"}. This record does not assert independent reproduction.

### RexOmni

mAP (0.5:0.95): 4. Result ID: 69b7ca3a47f34ce9249fb050.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1c1e209131cea8c69b.md>)

[Implementation](<https://github.com/IDEA-Research/Rex-Omni>)

Recorded evaluation configuration: {"Prompt":"Human-Prompt"}. This record does not assert independent reproduction.

### GroundingDINO

mAP (0.5:0.95): 4. Result ID: 69b7ca3a47f34ce9249fb052.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6055d.md>)

[Implementation](<https://github.com/IDEA-Research/GroundingDINO>)

Recorded evaluation configuration: {"Prompt":"Human-Prompt"}. This record does not assert independent reproduction.

### YoloWorld

mAP (0.5:0.95): 2. Result ID: 69b7ca3a47f34ce9249fb054.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72411e209131cea554fe.md>)

Recorded evaluation configuration: {"Prompt":"Human-Prompt"}. This record does not assert independent reproduction.

### GroundingDINO

mAP (0.5:0.95): 0. Result ID: 69b7ca3a47f34ce9249fb051.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6055d.md>)

[Implementation](<https://github.com/IDEA-Research/GroundingDINO>)

Recorded evaluation configuration: {"Prompt":"GPT-Prompt"}. This record does not assert independent reproduction.

### YoloWorld

mAP (0.5:0.95): 0. Result ID: 69b7ca3a47f34ce9249fb053.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e670636e5bf4afbdaa3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72411e209131cea554fe.md>)

Recorded evaluation configuration: {"Prompt":"GPT-Prompt"}. This record does not assert independent reproduction.

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