# Image Classification on Fashion-MNIST (Accuracy Trials)

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

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

Data updated: 2026-05-20T08:44:02.196Z

Evaluation of Image Classification performance on the Fashion-MNIST dataset, reporting Top-1 Accuracy across multiple trials, including mean and standard deviation statistics.

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 |
| Metric | Top-1 Accuracy (Best) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Top-1 Accuracy (Best)](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-accuracy-trials.md?metric=Top-1%20Accuracy%20(Best)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Final)](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-accuracy-trials.md?metric=Top-1%20Accuracy%20(Final)>): Higher is better; unit: PERCENT.

- [Mean Top-1 Accuracy (Best)](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-accuracy-trials.md?metric=Mean%20Top-1%20Accuracy%20(Best)>): Higher is better; unit: PERCENT.

- [Std Dev Top-1 Accuracy (Best)](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-accuracy-trials.md?metric=Std%20Dev%20Top-1%20Accuracy%20(Best)>): Lower is better; unit: PERCENT.

- [Mean Top-1 Accuracy (Final)](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-accuracy-trials.md?metric=Mean%20Top-1%20Accuracy%20(Final)>): Higher is better; unit: PERCENT.

- [Std Dev Top-1 Accuracy (Final)](<https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-accuracy-trials.md?metric=Std%20Dev%20Top-1%20Accuracy%20(Final)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (Best) | Result date | Report paper |
| --- | --- | --- | --- |
| TIDE | 94.24 | Not recorded | 6a0d4045f984739ed6737a02 |
| CTM | 92.8 | Not recorded | 6a0d4045f984739ed6737a02 |

### TIDE

Top-1 Accuracy (Best): 94.24. Result ID: 6a0d72aafbc373592c05821a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4045f984739ed6737a02.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d4045f984739ed6737a02.md>)

Recorded evaluation configuration: {"dmodel":"256","Backbone":"HRF","Steps":"50K"}. This record does not assert independent reproduction.

### CTM

Top-1 Accuracy (Best): 92.8. Result ID: 6a0d72aafbc373592c05821b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4045f984739ed6737a02.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd71e209131cea8ad91.md>)

Recorded evaluation configuration: {"dmodel":"256","Backbone":"HRF","Steps":"200K"}. This record does not assert independent reproduction.

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