# Image Classification on CIFAR-100 (Symmetric/Asymmetric Accuracy)

Source: [Image Classification on CIFAR-100 (Symmetric/Asymmetric Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-symmetric-asymmetric-accuracy>)

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

Data updated: 2026-05-19T10:12:11.587Z

Evaluation of Image Classification performance on the CIFAR-100 dataset, reporting specialized accuracy metrics including Symmetric 20%, Symmetric 50%, and Asymmetric 40% Accuracy.

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 |
| Metric | Symmetric 20% Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Symmetric 20% Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-symmetric-asymmetric-accuracy.md?metric=Symmetric%2020%25%20Accuracy>): Higher is better; unit: PERCENT.

- [Symmetric 50% Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-symmetric-asymmetric-accuracy.md?metric=Symmetric%2050%25%20Accuracy>): Higher is better; unit: PERCENT.

- [Asymmetric 40% Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-symmetric-asymmetric-accuracy.md?metric=Asymmetric%2040%25%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-symmetric-asymmetric-accuracy.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Symmetric 20% Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| RGC | 73.7 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| IDO | 70.8 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| EarlyCut | 63.7 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| DCD | 63.3 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| DivideMix | 61.6 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| LongReMix | 61.3 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| RRL | 61 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| UNICON | 60.7 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| PSSCL | 56.5 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| ProMix | 55.2 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| GCE | 50.1 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| Standard CE | 44.6 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |
| L2B | 42.9 | Not recorded | 6a0bee9fdbc836b87d82c4b6 |

### RGC

Symmetric 20% Accuracy: 73.7. Result ID: 6a0c3734fbc373592c02de42.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

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

### IDO

Symmetric 20% Accuracy: 70.8. Result ID: 6a0c3734fbc373592c02de41.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790b1e209131cea7bdab.md>)

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

### EarlyCut

Symmetric 20% Accuracy: 63.7. Result ID: 6a0c3734fbc373592c02de40.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c701e209131cea8e128.md>)

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

### DCD

Symmetric 20% Accuracy: 63.3. Result ID: 6a0c3734fbc373592c02de3f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

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

### DivideMix

Symmetric 20% Accuracy: 61.6. Result ID: 6a0c3734fbc373592c02de38.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.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.

### LongReMix

Symmetric 20% Accuracy: 61.3. Result ID: 6a0c3734fbc373592c02de3c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d5a1e209131cea39623.md>)

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

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

### RRL

Symmetric 20% Accuracy: 61. Result ID: 6a0c3734fbc373592c02de39.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

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

### UNICON

Symmetric 20% Accuracy: 60.7. Result ID: 6a0c3734fbc373592c02de3a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c691e209131cea33eab.md>)

[Implementation](<https://github.com/nazmul-karim170/UNICON-Noisy-Label>)

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

### PSSCL

Symmetric 20% Accuracy: 56.5. Result ID: 6a0c3734fbc373592c02de3e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

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

### ProMix

Symmetric 20% Accuracy: 55.2. Result ID: 6a0c3734fbc373592c02de3b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703e1e209131cea49ea2.md>)

[Implementation](<https://github.com/Justherozen/ProMix>)

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

### GCE

Symmetric 20% Accuracy: 50.1. Result ID: 6a0c3734fbc373592c02de37.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

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

### Standard CE

Symmetric 20% Accuracy: 44.6. Result ID: 6a0c3734fbc373592c02de36.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

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

### L2B

Symmetric 20% Accuracy: 42.9. Result ID: 6a0c3734fbc373592c02de3d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee9fdbc836b87d82c4b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ab1e209131cea57bd9.md>)

[Implementation](<https://github.com/yuyinzhou/l2b>)

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.
