# Object Detection on Mask Wearing

Source: [Object Detection on Mask Wearing](<https://www.sota2.com/research/sota/object-detection-on-mask-wearing>)

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

Data updated: 2026-02-26T05:22:41.664Z

Evaluation of Object Detection performance on the Mask Wearing dataset.

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) | Mask Wearing |
| Metric | AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [AP](<https://www.sota2.com/research/sota/object-detection-on-mask-wearing.md?metric=AP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| DyHead-Swin-L | 52 | Not recorded | 68fa6b451e209131cea2d291 |
| DyHead-Swin-L | 26.8 | Not recorded | 68fa6b451e209131cea2d291 |
| Florence | 15 | Not recorded | 68fa6b451e209131cea2d291 |
| ZSD | 0.6 | Not recorded | 68fa6b451e209131cea2d291 |

### DyHead-Swin-L

AP: 52. Result ID: 698e7685ffc3901de09dcb35.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b451e209131cea2d291.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2c1e209131cea269b7.md>)

[Implementation](<https://github.com/microsoft/DynamicHead>)

Recorded evaluation configuration: {"Protocol":"Fine-tuned","Condition":"full"}. This record does not assert independent reproduction.

### DyHead-Swin-L

AP: 26.8. Result ID: 698e7685ffc3901de09dcb36.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b451e209131cea2d291.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2c1e209131cea269b7.md>)

[Implementation](<https://github.com/microsoft/DynamicHead>)

Recorded evaluation configuration: {"Protocol":"Fine-tuned","Condition":"5-shot"}. This record does not assert independent reproduction.

### Florence

AP: 15. Result ID: 698e7685ffc3901de09dcb38.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b451e209131cea2d291.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b451e209131cea2d291.md>)

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

### ZSD

AP: 0.6. Result ID: 698e7685ffc3901de09dcb37.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b451e209131cea2d291.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64a61e209131cea05dfb.md>)

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

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