# Image Classification on CIFAR-100 (test) (Asymmetric Noise Robustness)

Source: [Image Classification on CIFAR-100 (test) (Asymmetric Noise Robustness)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-asymmetric-noise-robustness>)

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

Data updated: 2026-02-26T06:06:10.822Z

Evaluation of Image Classification performance on the CIFAR-100 test set, specifically measuring accuracy under varying levels of asymmetric input noise (20%, 30%, 40%).

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-100 (test) |
| Metric | Test Acc (asym-20%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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 Acc (asym-20%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-asymmetric-noise-robustness.md?metric=Test%20Acc%20(asym-20%25)>): Higher is better; unit: PERCENT.

- [Test Acc (asym-30%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-asymmetric-noise-robustness.md?metric=Test%20Acc%20(asym-30%25)>): Higher is better; unit: PERCENT.

- [Test Acc (asym-40%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-asymmetric-noise-robustness.md?metric=Test%20Acc%20(asym-40%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Test Acc (asym-20%) | Result date | Report paper |
| --- | --- | --- | --- |
| Co-learning+HCR | 68.85 | Not recorded | 68fa6cb81e209131cea358e5 |
| Co-learning | 65.26 | Not recorded | 68fa6cb81e209131cea358e5 |
| Co-teaching | 59.76 | Not recorded | 68fa6cb81e209131cea358e5 |
| Standard CE | 59.36 | Not recorded | 68fa6cb81e209131cea358e5 |
| JoCoR | 58.58 | Not recorded | 68fa6cb81e209131cea358e5 |
| Decoupling | 57.97 | Not recorded | 68fa6cb81e209131cea358e5 |
| Co-teaching+ | 56.11 | Not recorded | 68fa6cb81e209131cea358e5 |

### Co-learning+HCR

Test Acc (asym-20%): 68.85. Result ID: 698f35413a6c314849f70283.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":5,"Evaluation window":"last 10 epochs"}. This record does not assert independent reproduction.

### Co-learning

Test Acc (asym-20%): 65.26. Result ID: 698f35413a6c314849f70282.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2e1e209131cea2ca11.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":5,"Evaluation window":"last 10 epochs"}. This record does not assert independent reproduction.

### Co-teaching

Test Acc (asym-20%): 59.76. Result ID: 698f35413a6c314849f7027f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":5,"Evaluation window":"last 10 epochs"}. This record does not assert independent reproduction.

### Standard CE

Test Acc (asym-20%): 59.36. Result ID: 698f35413a6c314849f7027d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":5,"Evaluation window":"last 10 epochs"}. This record does not assert independent reproduction.

### JoCoR

Test Acc (asym-20%): 58.58. Result ID: 698f35413a6c314849f70281.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":5,"Evaluation window":"last 10 epochs"}. This record does not assert independent reproduction.

### Decoupling

Test Acc (asym-20%): 57.97. Result ID: 698f35413a6c314849f7027e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":5,"Evaluation window":"last 10 epochs"}. This record does not assert independent reproduction.

### Co-teaching+

Test Acc (asym-20%): 56.11. Result ID: 698f35413a6c314849f70280.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":5,"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.