# Image Classification on FashionMNIST (Accuracy, Val Loss, Loss Var.)

Source: [Image Classification on FashionMNIST (Accuracy, Val Loss, Loss Var.)](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-accuracy-val-loss-loss-var>)

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

Data updated: 2026-05-26T08:51:15.608Z

Evaluation of Image Classification performance on the FashionMNIST dataset, reporting standard accuracy, validation loss, and the variance of the validation loss.

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 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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-accuracy-val-loss-loss-var.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Validation Loss](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-accuracy-val-loss-loss-var.md?metric=Validation%20Loss>): Lower is better; unit: SCALAR.

- [Validation Loss Variance](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-accuracy-val-loss-loss-var.md?metric=Validation%20Loss%20Variance>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PILOT | 0.9413 | Not recorded | 6a152933dbd7150506f7e017 |
| AdaBelief | 0.9366 | Not recorded | 6a152933dbd7150506f7e017 |
| Adam | 0.9328 | Not recorded | 6a152933dbd7150506f7e017 |
| AdamW | 0.9322 | Not recorded | 6a152933dbd7150506f7e017 |
| Lion | 0.9291 | Not recorded | 6a152933dbd7150506f7e017 |
| Sophia | 0.8914 | Not recorded | 6a152933dbd7150506f7e017 |

### PILOT

Accuracy: 0.9413. Result ID: 6a155efcfbc373592c0ce345.

[Reporting paper](<https://www.sota2.com/research/paper/6a152933dbd7150506f7e017.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152933dbd7150506f7e017.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

### AdaBelief

Accuracy: 0.9366. Result ID: 6a155efcfbc373592c0ce344.

[Reporting paper](<https://www.sota2.com/research/paper/6a152933dbd7150506f7e017.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f282.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

### Adam

Accuracy: 0.9328. Result ID: 6a155efcfbc373592c0ce340.

[Reporting paper](<https://www.sota2.com/research/paper/6a152933dbd7150506f7e017.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fca0b.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

### AdamW

Accuracy: 0.9322. Result ID: 6a155efcfbc373592c0ce341.

[Reporting paper](<https://www.sota2.com/research/paper/6a152933dbd7150506f7e017.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa55761e209131ce9946db.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

### Lion

Accuracy: 0.9291. Result ID: 6a155efcfbc373592c0ce342.

[Reporting paper](<https://www.sota2.com/research/paper/6a152933dbd7150506f7e017.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea448e3.md>)

[Implementation](<https://github.com/google/automl/tree/master/lion>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

### Sophia

Accuracy: 0.8914. Result ID: 6a155efcfbc373592c0ce343.

[Reporting paper](<https://www.sota2.com/research/paper/6a152933dbd7150506f7e017.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5b801e209131ce9c8f96.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

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