# Image Classification on Fashion-MNIST (seasonal setup)

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

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

Data updated: 2026-02-26T05:45:15.213Z

Evaluation of model classification performance on the specific 'seasonal setup' split of the Fashion-MNIST dataset, reporting final and peak accuracy.

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 | Classification |
| Dataset (including any stated split) | Fashion-MNIST seasonal setup |
| Metric | Final 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

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

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

## Recorded results

| Method | Final Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Centralized Baseline | 88 | Not recorded | 69705de7e25ad2fa9d1ed776 |
| FedAvg (no drift) | 78 | Not recorded | 69705de7e25ad2fa9d1ed776 |
| FedAvg + Replay | 78 | Not recorded | 69705de7e25ad2fa9d1ed776 |
| FedAvg (with drift) | 28 | Not recorded | 69705de7e25ad2fa9d1ed776 |

### Centralized Baseline

Final Accuracy: 88. Result ID: 69992de85698665ec4965989.

[Reporting paper](<https://www.sota2.com/research/paper/69705de7e25ad2fa9d1ed776.md>)

Recorded evaluation configuration: {"Notes":"IID only, no drift"}. This record does not assert independent reproduction.

### FedAvg (no drift)

Final Accuracy: 78. Result ID: 69992de85698665ec496598a.

[Reporting paper](<https://www.sota2.com/research/paper/69705de7e25ad2fa9d1ed776.md>)

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

Recorded evaluation configuration: {"Notes":"Stable IID training"}. This record does not assert independent reproduction.

### FedAvg + Replay

Final Accuracy: 78. Result ID: 69992de85698665ec496598c.

[Reporting paper](<https://www.sota2.com/research/paper/69705de7e25ad2fa9d1ed776.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705de7e25ad2fa9d1ed776.md>)

Recorded evaluation configuration: {"Notes":"50 samples/class buffer"}. This record does not assert independent reproduction.

### FedAvg (with drift)

Final Accuracy: 28. Result ID: 69992de85698665ec496598b.

[Reporting paper](<https://www.sota2.com/research/paper/69705de7e25ad2fa9d1ed776.md>)

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

Recorded evaluation configuration: {"Notes":"Severe forgetting"}. This record does not assert independent reproduction.

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