# Synthetic Image Quality Assessment on ISIC 2018 (test)

Source: [Synthetic Image Quality Assessment on ISIC 2018 (test)](<https://www.sota2.com/research/sota/synthetic-image-quality-assessment-on-isic-2018-test>)

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

Data updated: 2026-02-26T05:44:34.120Z

Evaluation of synthetic image quality assessment models on the test split of the ISIC 2018 dataset, using metrics such as FID, KID, CLIP-I, LPIPS, CMMD, and MOS.

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 | Synthetic Image Quality Assessment |
| Dataset (including any stated split) | ISIC 2018 (test) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/synthetic-image-quality-assessment-on-isic-2018-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [KID](<https://www.sota2.com/research/sota/synthetic-image-quality-assessment-on-isic-2018-test.md?metric=KID>): Lower is better; unit: SCALAR.

- [CLIP-I](<https://www.sota2.com/research/sota/synthetic-image-quality-assessment-on-isic-2018-test.md?metric=CLIP-I>): Higher is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/synthetic-image-quality-assessment-on-isic-2018-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [CMMD](<https://www.sota2.com/research/sota/synthetic-image-quality-assessment-on-isic-2018-test.md?metric=CMMD>): Lower is better; unit: SCALAR.

- [MOS](<https://www.sota2.com/research/sota/synthetic-image-quality-assessment-on-isic-2018-test.md?metric=MOS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Siamese-Diffusion | 44.036 | Not recorded | 68fa78821e209131cea78c41 |
| ControlNet | 45.49 | Not recorded | 68fa78821e209131cea78c41 |
| T2I-Adapter | 224.446 | Not recorded | 68fa78821e209131cea78c41 |

### Siamese-Diffusion

FID: 44.036. Result ID: 69958ed83badfaffe688cc15.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78821e209131cea78c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78821e209131cea78c41.md>)

[Implementation](<https://github.com/Qiukunpeng/Siamese-Diffusion>)

Recorded evaluation configuration: {"input\_type":"mask-only"}. This record does not assert independent reproduction.

### ControlNet

FID: 45.49. Result ID: 69958ed83badfaffe688cc14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78821e209131cea78c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

Recorded evaluation configuration: {"input\_type":"mask-only"}. This record does not assert independent reproduction.

### T2I-Adapter

FID: 224.446. Result ID: 69958ed83badfaffe688cc13.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78821e209131cea78c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecf1e209131cea42531.md>)

Recorded evaluation configuration: {"input\_type":"mask-only"}. This record does not assert independent reproduction.

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