# Image Classification on Red Mini-ImageNet (0.6 Noise Rate CNWL Test)

Source: [Image Classification on Red Mini-ImageNet (0.6 Noise Rate CNWL Test)](<https://www.sota2.com/research/sota/image-classification-on-red-mini-imagenet-0-6-noise-rate-cnwl-test>)

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

Data updated: 2026-02-26T05:28:29.097Z

Evaluation of Image Classification performance on the Red Mini-ImageNet subset corrupted by 60% noise derived from Controlled Noisy Web Labels (CNWL) test set.

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) | Red Mini-ImageNet 0.6 noise rate Controlled Noisy Web Labels (CNWL) (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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](<https://www.sota2.com/research/sota/image-classification-on-red-mini-imagenet-0-6-noise-rate-cnwl-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| InstanceGM-SS | 53.21 | Not recorded | 68fa6d591e209131cea395bc |
| PropMix | 52.84 | Not recorded | 68fa6d591e209131cea395bc |
| InstanceGM | 47.96 | Not recorded | 68fa6d591e209131cea395bc |
| FaMUS | 45.1 | Not recorded | 68fa6d591e209131cea395bc |
| MentorMix | 43.8 | Not recorded | 68fa6d591e209131cea395bc |
| DivideMix | 43.14 | Not recorded | 68fa6d591e209131cea395bc |
| MixUp | 40.58 | Not recorded | 68fa6d591e209131cea395bc |
| CE | 37.3 | Not recorded | 68fa6d591e209131cea395bc |

### InstanceGM-SS

Accuracy: 53.21. Result ID: 698f9dad3a6c314849fa8c2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Implementation](<https://github.com/a5507203/IDLN/blob/main/causalNL.py>)

Recorded evaluation configuration: {"self-supervised learning":true}. This record does not assert independent reproduction.

### PropMix

Accuracy: 52.84. Result ID: 698f9dad3a6c314849fa8c29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c2f6.md>)

[Implementation](<https://github.com/filipe-research/PropMix>)

Recorded evaluation configuration: {"self-supervised learning":true}. This record does not assert independent reproduction.

### InstanceGM

Accuracy: 47.96. Result ID: 698f9dad3a6c314849fa8c28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Implementation](<https://github.com/a5507203/IDLN/blob/main/causalNL.py>)

Recorded evaluation configuration: {"self-supervised learning":false}. This record does not assert independent reproduction.

### FaMUS

Accuracy: 45.1. Result ID: 698f9dad3a6c314849fa8c27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d11e209131cea245ef.md>)

[Implementation](<https://github.com/youjiangxu/FaMUS>)

Recorded evaluation configuration: {"self-supervised learning":false}. This record does not assert independent reproduction.

### MentorMix

Accuracy: 43.8. Result ID: 698f9dad3a6c314849fa8c26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68321e209131cea1aab4.md>)

[Implementation](<http://www.lujiang.info/cnlw.html>)

Recorded evaluation configuration: {"self-supervised learning":false}. This record does not assert independent reproduction.

### DivideMix

Accuracy: 43.14. Result ID: 698f9dad3a6c314849fa8c25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

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

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

Recorded evaluation configuration: {"self-supervised learning":false}. This record does not assert independent reproduction.

### MixUp

Accuracy: 40.58. Result ID: 698f9dad3a6c314849fa8c24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e44.md>)

[Implementation](<https://github.com/facebookresearch/mixup-cifar10>)

Recorded evaluation configuration: {"self-supervised learning":false}. This record does not assert independent reproduction.

### CE

Accuracy: 37.3. Result ID: 698f9dad3a6c314849fa8c23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d591e209131cea395bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea35949.md>)

Recorded evaluation configuration: {"self-supervised learning":false}. This record does not assert independent reproduction.

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