# Image Classification on FashionMNIST NIID A

Source: [Image Classification on FashionMNIST NIID A](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-niid-a>)

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

Data updated: 2026-03-04T19:14:35.122Z

Evaluation of Image Classification performance on the Non-IID (NIID A) distribution split of the FashionMNIST dataset.

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) | FashionMNIST NIID A |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-niid-a.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| EdgeFLowRand | 87.97 | Not recorded | 69a7bc972d603e6de3e3d640 |
| EdgeFLowSeq | 87.5 | Not recorded | 69a7bc972d603e6de3e3d640 |
| FedAvg | 86.89 | Not recorded | 69a7bc972d603e6de3e3d640 |

### EdgeFLowRand

Accuracy: 87.97. Result ID: 69a884836dbb7075b950e7e6.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc972d603e6de3e3d640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a7bc972d603e6de3e3d640.md>)

Recorded evaluation configuration: {"Cluster size Nm":"10","Local epoch K":"5","Mini-batch size":"64","Backbone":"6-layer CNN"}. This record does not assert independent reproduction.

### EdgeFLowSeq

Accuracy: 87.5. Result ID: 69a884836dbb7075b950e7e7.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc972d603e6de3e3d640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a7bc972d603e6de3e3d640.md>)

Recorded evaluation configuration: {"Cluster size Nm":"10","Local epoch K":"5","Mini-batch size":"64","Backbone":"6-layer CNN"}. This record does not assert independent reproduction.

### FedAvg

Accuracy: 86.89. Result ID: 69a884836dbb7075b950e7e5.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc972d603e6de3e3d640.md>)

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

Recorded evaluation configuration: {"Cluster size Nm":"10","Local epoch K":"5","Mini-batch size":"64","Backbone":"6-layer CNN"}. This record does not assert independent reproduction.

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