# 2D Object Detection on HBD 20 (val)

Source: [2D Object Detection on HBD 20 (val)](<https://www.sota2.com/research/sota/2d-object-detection-on-hbd-20-val>)

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

Data updated: 2026-02-26T05:58:20.547Z

Evaluation of 2D Object Detection performance on the HBD 20 validation split, reporting Precision, Recall, F1 score, and Best Recall.

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 | 2D Object Detection |
| Dataset (including any stated split) | HBD 20 (val) |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Precision](<https://www.sota2.com/research/sota/2d-object-detection-on-hbd-20-val.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/2d-object-detection-on-hbd-20-val.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/2d-object-detection-on-hbd-20-val.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Best Recall](<https://www.sota2.com/research/sota/2d-object-detection-on-hbd-20-val.md?metric=Best%20Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| YOLO | 76 | Not recorded | 68fa6c181e209131cea321fc |
| OSOP | 43 | Not recorded | 68fa6c181e209131cea321fc |
| OS2D | 24 | Not recorded | 68fa6c181e209131cea321fc |

### YOLO

Precision: 76. Result ID: 698ed0efffc3901de0a19fc8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c181e209131cea321fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03af3.md>)

[Implementation](<https://pjreddie.com/yolo/>)

Recorded evaluation configuration: {"trained on target objects":true}. This record does not assert independent reproduction.

### OSOP

Precision: 43. Result ID: 698ed0efffc3901de0a19fc9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c181e209131cea321fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c181e209131cea321fc.md>)

Recorded evaluation configuration: {"trained on target objects":false,"paradigm":"one shot"}. This record does not assert independent reproduction.

### OS2D

Precision: 24. Result ID: 698ed0efffc3901de0a19fca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c181e209131cea321fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6b6.md>)

Recorded evaluation configuration: {"paradigm":"one shot"}. This record does not assert independent reproduction.

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