# Image Classification on CIFAR-10 with ImageNet-32 open-set noise

Source: [Image Classification on CIFAR-10 with ImageNet-32 open-set noise](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-with-imagenet-32-open-set-noise>)

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

Data updated: 2026-02-26T05:35:11.525Z

Evaluation of Image Classification performance on the CIFAR-10 dataset corrupted by open-set noise derived from ImageNet-32 samples.

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) | CIFAR-10 with ImageNet-32 open-set noise |
| Metric | Average Accuracy |
| 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

- [Average Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-with-imagenet-32-open-set-noise.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Max Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-with-imagenet-32-open-set-noise.md?metric=Max%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Co-teaching+ | 79.89 | Not recorded | 68fa65bb1e209131cea0bed4 |
| Co-teaching | 79.42 | Not recorded | 68fa65bb1e209131cea0bed4 |
| Iterative | 79.38 | Not recorded | 68fa65bb1e209131cea0bed4 |
| MentorNet | 79.27 | Not recorded | 68fa65bb1e209131cea0bed4 |
| Standard | 58.63 | Not recorded | 68fa65bb1e209131cea0bed4 |

### Co-teaching+

Average Accuracy: 79.89. Result ID: 698cc3c58b517eb4331c9302.

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

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

Recorded evaluation configuration: {"Noise ratio":"40%","Evaluation window":"Last 10 epochs"}. This record does not assert independent reproduction.

### Co-teaching

Average Accuracy: 79.42. Result ID: 698cc3c58b517eb4331c9301.

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

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

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

Recorded evaluation configuration: {"Noise ratio":"40%","Evaluation window":"Last 10 epochs"}. This record does not assert independent reproduction.

### Iterative

Average Accuracy: 79.38. Result ID: 698cc3c58b517eb4331c9300.

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

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

Recorded evaluation configuration: {"Noise ratio":"40%","Evaluation window":"Last 10 epochs"}. This record does not assert independent reproduction.

### MentorNet

Average Accuracy: 79.27. Result ID: 698cc3c58b517eb4331c92ff.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa64bf1e209131cea063ec.md>)

[Implementation](<https://github.com/google/mentornet>)

Recorded evaluation configuration: {"Noise ratio":"40%","Evaluation window":"Last 10 epochs"}. This record does not assert independent reproduction.

### Standard

Average Accuracy: 58.63. Result ID: 698cc3c58b517eb4331c92fe.

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

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

Recorded evaluation configuration: {"Noise ratio":"40%","Evaluation window":"Last 10 epochs"}. This record does not assert independent reproduction.

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