# Image Classification on CIFAR10 Noise ratio 0.3, Open ratio 1.0 (test)

Source: [Image Classification on CIFAR10 Noise ratio 0.3, Open ratio 1.0 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-noise-ratio-0-3-open-ratio-1-0-test>)

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

Data updated: 2026-02-26T05:37:44.225Z

Evaluation of Image Classification performance on the CIFAR-10 dataset corrupted with a 0.3 noise ratio (Open ratio 1.0) evaluated on the test split.

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) | CIFAR10 Noise ratio 0.3, Open ratio 1.0 (test) |
| Metric | Best 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

- [Best Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar10-noise-ratio-0-3-open-ratio-1-0-test.md?metric=Best%20Accuracy>): Higher is better; unit: PERCENT.

- [Last Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar10-noise-ratio-0-3-open-ratio-1-0-test.md?metric=Last%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Best Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SSR+ | 0.961 | Not recorded | 68fa74c31e209131cea639e7 |
| SSR | 0.957 | Not recorded | 68fa74c31e209131cea639e7 |
| EDM | 0.929 | Not recorded | 68fa74c31e209131cea639e7 |
| ROG | 0.914 | Not recorded | 68fa74c31e209131cea639e7 |
| ILON | 0.904 | Not recorded | 68fa74c31e209131cea639e7 |
| DivideMix | 0.893 | Not recorded | 68fa74c31e209131cea639e7 |

### SSR+

Best Accuracy: 0.961. Result ID: 69935a2e3a6c3148491553f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Implementation](<https://github.com/MrChenFeng/SSR_BMVC2022>)

Recorded evaluation configuration: {"co-training":true}. This record does not assert independent reproduction.

### SSR

Best Accuracy: 0.957. Result ID: 69935a2e3a6c3148491553f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Implementation](<https://github.com/MrChenFeng/SSR_BMVC2022>)

Recorded evaluation configuration: {"co-training":false}. This record does not assert independent reproduction.

### EDM

Best Accuracy: 0.929. Result ID: 69935a2e3a6c3148491553f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68b71e209131cea1dac6.md>)

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

### ROG

Best Accuracy: 0.914. Result ID: 69935a2e3a6c3148491553f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0bfcc.md>)

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

### ILON

Best Accuracy: 0.904. Result ID: 69935a2e3a6c3148491553ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea035aa.md>)

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

### DivideMix

Best Accuracy: 0.893. Result ID: 69935a2e3a6c3148491553f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671c1e209131cea144cf.md>)

[Implementation](<https://github.com/LiJunnan1992/DivideMix>)

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.