# Image Classification on Fashion-MNIST homogeneous (test)

Source: [Image Classification on Fashion-MNIST homogeneous (test)](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-homogeneous-test>)

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

Data updated: 2026-03-04T17:57:59.130Z

Evaluation of Image Classification performance on the specific homogeneous subset of the Fashion-MNIST test set, reporting accuracy and negative log-likelihood.

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 Classification |
| Dataset (including any stated split) | Fashion-MNIST homogeneous (test) |
| Metric | Test Accuracy |
| 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

- [Test Accuracy](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-homogeneous-test.md?metric=Test%20Accuracy>): Higher is better; unit: PERCENT.

- [Test NLL](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-homogeneous-test.md?metric=Test%20NLL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Test Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| IVON-ADMM | 84.1 | Not recorded | 68fa5da71e209131ce9dbecb |
| FedDyn | 75.3 | Not recorded | 68fa5da71e209131ce9dbecb |
| FedAvg | 72.3 | Not recorded | 68fa5da71e209131ce9dbecb |
| FedProx | 72.2 | Not recorded | 68fa5da71e209131ce9dbecb |

### IVON-ADMM

Test Accuracy: 84.1. Result ID: 69a872946dbb7075b9507056.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5da71e209131ce9dbecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5da71e209131ce9dbecb.md>)

Recorded evaluation configuration: {"Communication Rounds":"50","Posterior Averaging":"Full posterior"}. This record does not assert independent reproduction.

### FedDyn

Test Accuracy: 75.3. Result ID: 69a872946dbb7075b9507055.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5da71e209131ce9dbecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b361e209131cea2cecf.md>)

Recorded evaluation configuration: {"Communication Rounds":"10","Data Distribution":"Homogeneous"}. This record does not assert independent reproduction.

### FedAvg

Test Accuracy: 72.3. Result ID: 69a872946dbb7075b9507053.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5da71e209131ce9dbecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e761e209131cea40072.md>)

Recorded evaluation configuration: {"Communication Rounds":"10","Data Distribution":"Homogeneous"}. This record does not assert independent reproduction.

### FedProx

Test Accuracy: 72.2. Result ID: 69a872946dbb7075b9507054.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5da71e209131ce9dbecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67701e209131cea163fe.md>)

Recorded evaluation configuration: {"Communication Rounds":"10","Data Distribution":"Homogeneous"}. This record does not assert independent reproduction.

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