# Image Classification on MNIST Asymmetry-40% noise (test)

Source: [Image Classification on MNIST Asymmetry-40% noise (test)](<https://www.sota2.com/research/sota/image-classification-on-mnist-asymmetry-40-percent-noise-test>)

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

Data updated: 2026-02-26T06:06:11.435Z

Evaluation of Image Classification performance on the test split of the MNIST dataset corrupted specifically with 40% asymmetric noise.

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 Asymmetry-40% noise (test) |
| Metric | Test 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

- [Test Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-asymmetry-40-percent-noise-test.md?metric=Test%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Test Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| JoCoR | 95.24 | Not recorded | 68fa67711e209131cea164c7 |
| Co-teaching+ | 93.28 | Not recorded | 68fa67711e209131cea164c7 |
| Co-teaching | 90.28 | Not recorded | 68fa67711e209131cea164c7 |
| F-correction | 89.77 | Not recorded | 68fa67711e209131cea164c7 |
| Decoupling | 81.84 | Not recorded | 68fa67711e209131cea164c7 |
| Standard | 79 | Not recorded | 68fa67711e209131cea164c7 |

### JoCoR

Test Accuracy: 95.24. Result ID: 698d35e78b517eb4331fd26c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

Recorded evaluation configuration: {"Hardware":"NVIDIA Tesla V100 GPU"}. This record does not assert independent reproduction.

### Co-teaching+

Test Accuracy: 93.28. Result ID: 698d35e78b517eb4331fd26b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bb1e209131cea0bed4.md>)

Recorded evaluation configuration: {"Hardware":"NVIDIA Tesla V100 GPU"}. This record does not assert independent reproduction.

### Co-teaching

Test Accuracy: 90.28. Result ID: 698d35e78b517eb4331fd26a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64fe1e209131cea07aa4.md>)

[Implementation](<https://github.com/bhanML/Co-teaching>)

Recorded evaluation configuration: {"Hardware":"NVIDIA Tesla V100 GPU"}. This record does not assert independent reproduction.

### F-correction

Test Accuracy: 89.77. Result ID: 698d35e78b517eb4331fd268.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63321e209131ce9fd4c8.md>)

Recorded evaluation configuration: {"Hardware":"NVIDIA Tesla V100 GPU"}. This record does not assert independent reproduction.

### Decoupling

Test Accuracy: 81.84. Result ID: 698d35e78b517eb4331fd269.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642f1e209131cea0344e.md>)

Recorded evaluation configuration: {"Hardware":"NVIDIA Tesla V100 GPU"}. This record does not assert independent reproduction.

### Standard

Test Accuracy: 79. Result ID: 698d35e78b517eb4331fd267.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

Recorded evaluation configuration: {"Hardware":"NVIDIA Tesla V100 GPU"}. This record does not assert independent reproduction.

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