# Face Detection on Manga 109 Faces (test)

Source: [Face Detection on Manga 109 Faces (test)](<https://www.sota2.com/research/sota/face-detection-on-manga-109-faces-test>)

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

Data updated: 2026-02-26T05:22:46.298Z

Evaluation of face detection performance on the test split of the Manga 109 Faces dataset, measured using Average Precision (AP).

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 | Face Detection |
| Dataset (including any stated split) | Manga 109 Faces (test) |
| Metric | AP |
| 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

- [AP](<https://www.sota2.com/research/sota/face-detection-on-manga-109-faces-test.md?metric=AP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| XL Model w/ All Images | 87.88 | Not recorded | 68fa6f211e209131cea43e56 |
| Train w/ All Images | 87.86 | Not recorded | 68fa6f211e209131cea43e56 |
| Train w/ 512 Images | 85.15 | Not recorded | 68fa6f211e209131cea43e56 |
| Train w/ 256 Images | 84.2 | Not recorded | 68fa6f211e209131cea43e56 |
| Train w/ 64 Images | 80.41 | Not recorded | 68fa6f211e209131cea43e56 |
| Ogawa et al. | 76.2 | Not recorded | 68fa6f211e209131cea43e56 |
| Teacher-Student | 69.25 | Not recorded | 68fa6f211e209131cea43e56 |
| All Styles | 54.74 | Not recorded | 68fa6f211e209131cea43e56 |

### XL Model w/ All Images

AP: 87.88. Result ID: 699096d73a6c31484901aba4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Implementation](<https://github.com/barisbatuhan/DASS_Detector>)

Recorded evaluation configuration: {"Supervision Type":"FS","Training Images":"All","Model Architecture":"XL"}. This record does not assert independent reproduction.

### Train w/ All Images

AP: 87.86. Result ID: 699096d73a6c31484901aba3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Implementation](<https://github.com/barisbatuhan/DASS_Detector>)

Recorded evaluation configuration: {"Supervision Type":"FS","Training Images":"All"}. This record does not assert independent reproduction.

### Train w/ 512 Images

AP: 85.15. Result ID: 699096d73a6c31484901aba2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Implementation](<https://github.com/barisbatuhan/DASS_Detector>)

Recorded evaluation configuration: {"Supervision Type":"FS","Training Images":"512"}. This record does not assert independent reproduction.

### Train w/ 256 Images

AP: 84.2. Result ID: 699096d73a6c31484901aba1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Implementation](<https://github.com/barisbatuhan/DASS_Detector>)

Recorded evaluation configuration: {"Supervision Type":"FS","Training Images":"256"}. This record does not assert independent reproduction.

### Train w/ 64 Images

AP: 80.41. Result ID: 699096d73a6c31484901aba0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Implementation](<https://github.com/barisbatuhan/DASS_Detector>)

Recorded evaluation configuration: {"Supervision Type":"FS","Training Images":"64"}. This record does not assert independent reproduction.

### Ogawa et al.

AP: 76.2. Result ID: 699096d73a6c31484901aba5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642d1e209131cea03347.md>)

Recorded evaluation configuration: {"Supervision Type":"FS"}. This record does not assert independent reproduction.

### Teacher-Student

AP: 69.25. Result ID: 699096d73a6c31484901ab9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Implementation](<https://github.com/barisbatuhan/DASS_Detector>)

Recorded evaluation configuration: {"Supervision Type":"SS"}. This record does not assert independent reproduction.

### All Styles

AP: 54.74. Result ID: 699096d73a6c31484901ab9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e56.md>)

[Implementation](<https://github.com/barisbatuhan/DASS_Detector>)

Recorded evaluation configuration: {"Supervision Type":"NS"}. This record does not assert independent reproduction.

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