# Image Classification on MNIST uniform label noise η=0.2 (7-fold CV)

Source: [Image Classification on MNIST uniform label noise η=0.2 (7-fold CV)](<https://www.sota2.com/research/sota/image-classification-on-mnist-uniform-label-noise-0-2-7-fold-cv>)

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

Data updated: 2026-03-19T09:40:55.814Z

Evaluation of Image Classification performance on the MNIST dataset corrupted with 20% uniform label noise, assessed via 7-fold cross-validation.

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) | MNIST uniform label noise η=0.2 (7-fold CV) |
| Metric | Accuracy (7-fold CV) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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 (7-fold CV)](<https://www.sota2.com/research/sota/image-classification-on-mnist-uniform-label-noise-0-2-7-fold-cv.md?metric=Accuracy%20(7-fold%20CV)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (7-fold CV) | Result date | Report paper |
| --- | --- | --- | --- |
| rSDNet | 97.43 | Not recorded | 69bb83270636e5bf4afc1bf1 |
| rSDNet | 97.31 | Not recorded | 69bb83270636e5bf4afc1bf1 |
| GCE | 97.31 | Not recorded | 69bb83270636e5bf4afc1bf1 |
| MAE | 97.2 | Not recorded | 69bb83270636e5bf4afc1bf1 |
| CCE | 75.28 | Not recorded | 69bb83270636e5bf4afc1bf1 |

### rSDNet

Accuracy (7-fold CV): 97.43. Result ID: 69bbc4a247f34ce924a60b42.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83270636e5bf4afc1bf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb83270636e5bf4afc1bf1.md>)

Recorded evaluation configuration: {"beta":"0","lambda":"-0.8"}. This record does not assert independent reproduction.

### rSDNet

Accuracy (7-fold CV): 97.31. Result ID: 69bbc4a247f34ce924a60b41.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83270636e5bf4afc1bf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb83270636e5bf4afc1bf1.md>)

Recorded evaluation configuration: {"beta":"0.05","lambda":"-1"}. This record does not assert independent reproduction.

### GCE

Accuracy (7-fold CV): 97.31. Result ID: 69bbc4a247f34ce924a60b43.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83270636e5bf4afc1bf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

Recorded evaluation configuration: {"q":"0.7"}. This record does not assert independent reproduction.

### MAE

Accuracy (7-fold CV): 97.2. Result ID: 69bbc4a247f34ce924a60b40.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83270636e5bf4afc1bf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63e81e209131cea0158c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CCE

Accuracy (7-fold CV): 75.28. Result ID: 69bbc4a247f34ce924a60b3f.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83270636e5bf4afc1bf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64aa1e209131cea05fc7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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