# Facial attractiveness estimation on SCUT-FBP 20% (test)

Source: [Facial attractiveness estimation on SCUT-FBP 20% (test)](<https://www.sota2.com/research/sota/facial-attractiveness-estimation-on-scut-fbp-20-percent-test>)

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

Data updated: 2026-02-26T05:48:57.549Z

Evaluation of models performing Facial attractiveness estimation on the 20% test split of the SCUT-FBP dataset, reporting regression metrics such as MAE, RMSE, and PC.

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 | Facial attractiveness estimation |
| Dataset (including any stated split) | SCUT-FBP 20% (test) |
| Metric | MAE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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

- [MAE](<https://www.sota2.com/research/sota/facial-attractiveness-estimation-on-scut-fbp-20-percent-test.md?metric=MAE>): Lower is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/facial-attractiveness-estimation-on-scut-fbp-20-percent-test.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [PC](<https://www.sota2.com/research/sota/facial-attractiveness-estimation-on-scut-fbp-20-percent-test.md?metric=PC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | MAE | Result date | Report paper |
| --- | --- | --- | --- |
| DLDL-v2 (ThinAttNet) | 0.212 | Not recorded | 68fa6b861e209131cea2ed1b |
| LDL | 0.213 | Not recorded | 68fa6b861e209131cea2ed1b |
| LDL | 0.217 | Not recorded | 68fa6b861e209131cea2ed1b |
| DLDL-v2 (TinyAttNet) | 0.221 | Not recorded | 68fa6b861e209131cea2ed1b |
| DALDL | 0.227 | Not recorded | 68fa6b861e209131cea2ed1b |
| R2-ResNeXt | 0.242 | Not recorded | 68fa6b861e209131cea2ed1b |
| MT-ResNet | 0.246 | Not recorded | 68fa6b861e209131cea2ed1b |
| SLDL | 0.302 | Not recorded | 68fa6b861e209131cea2ed1b |
| Regression | 0.393 | Not recorded | 68fa6b861e209131cea2ed1b |

### DLDL-v2 (ThinAttNet)

MAE: 0.212. Result ID: 698e93e5ffc3901de09ed0a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

Recorded evaluation configuration: {"Model":"Thin VGG-16"}. This record does not assert independent reproduction.

### LDL

MAE: 0.213. Result ID: 698e93e5ffc3901de09ed09d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62bb1e209131ce9fae9e.md>)

Recorded evaluation configuration: {"Venue":"TMM","Year":"2017","Model":"ResNet-50+GFeats","Feature Fusion":"multi-features fusion"}. This record does not assert independent reproduction.

### LDL

MAE: 0.217. Result ID: 698e93e5ffc3901de09ed09c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62bb1e209131ce9fae9e.md>)

Recorded evaluation configuration: {"Venue":"TMM","Year":"2017","Model":"ResNet-50"}. This record does not assert independent reproduction.

### DLDL-v2 (TinyAttNet)

MAE: 0.221. Result ID: 698e93e5ffc3901de09ed0a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

Recorded evaluation configuration: {"Model":"Tiny VGG-16"}. This record does not assert independent reproduction.

### DALDL

MAE: 0.227. Result ID: 698e93e5ffc3901de09ed09f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

Recorded evaluation configuration: {"Venue":"CCBR","Year":"2019","Model":"VGG-16"}. This record does not assert independent reproduction.

### R2-ResNeXt

MAE: 0.242. Result ID: 698e93e5ffc3901de09ed09e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

Recorded evaluation configuration: {"Venue":"ICPR","Year":"2018","Model":"ResNeXt"}. This record does not assert independent reproduction.

### MT-ResNet

MAE: 0.246. Result ID: 698e93e5ffc3901de09ed0a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

Recorded evaluation configuration: {"Venue":"CDS","Year":"2021","Model":"ResNet-50"}. This record does not assert independent reproduction.

### SLDL

MAE: 0.302. Result ID: 698e93e5ffc3901de09ed09a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

Recorded evaluation configuration: {"Venue":"IJCAI","Year":"2017","Model":"LBP+Hog+Gabor","Evaluation Protocol":"ten-fold cross validation"}. This record does not assert independent reproduction.

### Regression

MAE: 0.393. Result ID: 698e93e5ffc3901de09ed099.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b861e209131cea2ed1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62291e209131ce9f7b57.md>)

Recorded evaluation configuration: {"Venue":"SMC","Year":"2015","Model":"G+Tfeats"}. This record does not assert independent reproduction.

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