# Image Generation Quality Evaluation on BreastMNIST (test)

Source: [Image Generation Quality Evaluation on BreastMNIST (test)](<https://www.sota2.com/research/sota/image-generation-quality-evaluation-on-breastmnist-test>)

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

Data updated: 2026-02-26T05:44:43.197Z

Evaluation of generative model output quality on the test split of the BreastMNIST dataset, using metrics such as FID, Density, and Coverage.

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 | Image Generation Quality Evaluation |
| Dataset (including any stated split) | BreastMNIST (test) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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/image-generation-quality-evaluation-on-breastmnist-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [Density](<https://www.sota2.com/research/sota/image-generation-quality-evaluation-on-breastmnist-test.md?metric=Density>): Higher is better; unit: SCALAR.

- [Coverage](<https://www.sota2.com/research/sota/image-generation-quality-evaluation-on-breastmnist-test.md?metric=Coverage>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| GAN Ensembles (G\*) | 3.9 | Not recorded | 68fa77af1e209131cea74b66 |
| Single | 4.551 | Not recorded | 68fa77af1e209131cea74b66 |
| Naive | 4.759 | Not recorded | 68fa77af1e209131cea74b66 |
| Naive | 6.279 | Not recorded | 68fa77af1e209131cea74b66 |
| Single | 15.621 | Not recorded | 68fa77af1e209131cea74b66 |

### GAN Ensembles (G\*)

FID: 3.9. Result ID: 699a470f5698665ec4ce586d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b66.md>)

Recorded evaluation configuration: {"Selection strategy":"Proposed Ensemble Selection"}. This record does not assert independent reproduction.

### Single

FID: 4.551. Result ID: 699a470f5698665ec4ce5869.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b66.md>)

Recorded evaluation configuration: {"Selection strategy":"top-1"}. This record does not assert independent reproduction.

### Naive

FID: 4.759. Result ID: 699a470f5698665ec4ce586c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b66.md>)

Recorded evaluation configuration: {"Selection strategy":"A"}. This record does not assert independent reproduction.

### Naive

FID: 6.279. Result ID: 699a470f5698665ec4ce586b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b66.md>)

Recorded evaluation configuration: {"Selection strategy":"R"}. This record does not assert independent reproduction.

### Single

FID: 15.621. Result ID: 699a470f5698665ec4ce586a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b66.md>)

Recorded evaluation configuration: {"Selection strategy":"average"}. This record does not assert independent reproduction.

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