# Image Classification on CIFAR-10 (test) (Symmetric/Asymmetric Accuracy)

Source: [Image Classification on CIFAR-10 (test) (Symmetric/Asymmetric Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-symmetric-asymmetric-accuracy>)

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

Data updated: 2026-02-26T05:34:27.797Z

Evaluation of Image Classification performance on the CIFAR-10 test set using specialized accuracy metrics based on symmetric and asymmetric thresholds (20%, 50%, 80%, 90%, 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-10 (test) |
| Metric | Accuracy (Symmetric 20%) |
| 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

- [Accuracy (Symmetric 20%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-symmetric-asymmetric-accuracy.md?metric=Accuracy%20(Symmetric%2020%25)>): Higher is better; unit: PERCENT.

- [Accuracy (Symmetric 50%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-symmetric-asymmetric-accuracy.md?metric=Accuracy%20(Symmetric%2050%25)>): Higher is better; unit: PERCENT.

- [Accuracy (Symmetric 80%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-symmetric-asymmetric-accuracy.md?metric=Accuracy%20(Symmetric%2080%25)>): Higher is better; unit: PERCENT.

- [Accuracy (Symmetric 90%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-symmetric-asymmetric-accuracy.md?metric=Accuracy%20(Symmetric%2090%25)>): Higher is better; unit: PERCENT.

- [Accuracy (Asymmetric 40%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-symmetric-asymmetric-accuracy.md?metric=Accuracy%20(Asymmetric%2040%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Symmetric 20%) | Result date | Report paper |
| --- | --- | --- | --- |
| SSR+ | 96.7 | Not recorded | 68fa74c31e209131cea639e7 |
| C2D | 96.4 | Not recorded | 68fa74c31e209131cea639e7 |
| AugDesc | 96.3 | Not recorded | 68fa74c31e209131cea639e7 |
| SSR | 96.3 | Not recorded | 68fa74c31e209131cea639e7 |
| DivideMix | 96.1 | Not recorded | 68fa74c31e209131cea639e7 |
| NGC | 95.9 | Not recorded | 68fa74c31e209131cea639e7 |
| ELR+ | 95.8 | Not recorded | 68fa74c31e209131cea639e7 |
| RRL | 95.8 | Not recorded | 68fa74c31e209131cea639e7 |
| LossModelling | 94 | Not recorded | 68fa74c31e209131cea639e7 |
| PENCIL | 92.4 | Not recorded | 68fa74c31e209131cea639e7 |
| Co-teaching+ | 89.5 | Not recorded | 68fa74c31e209131cea639e7 |
| Cross-Entropy | 86.8 | Not recorded | 68fa74c31e209131cea639e7 |
| F-correction | 86.8 | Not recorded | 68fa74c31e209131cea639e7 |

### SSR+

Accuracy (Symmetric 20%): 96.7. Result ID: 69935a2e3a6c3148491553ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Implementation](<https://github.com/MrChenFeng/SSR_BMVC2022>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### C2D

Accuracy (Symmetric 20%): 96.4. Result ID: 69935a2e3a6c3148491553cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd31e209131cea305cf.md>)

[Implementation](<https://github.com/ContrastToDivide/C2D>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":true}. This record does not assert independent reproduction.

### AugDesc

Accuracy (Symmetric 20%): 96.3. Result ID: 69935a2e3a6c3148491553cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea2384c.md>)

[Implementation](<https://github.com/KentoNishi/Augmentation-for-LNL>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":true}. This record does not assert independent reproduction.

### SSR

Accuracy (Symmetric 20%): 96.3. Result ID: 69935a2e3a6c3148491553cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Implementation](<https://github.com/MrChenFeng/SSR_BMVC2022>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### DivideMix

Accuracy (Symmetric 20%): 96.1. Result ID: 69935a2e3a6c3148491553c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

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

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

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":true}. This record does not assert independent reproduction.

### NGC

Accuracy (Symmetric 20%): 95.9. Result ID: 69935a2e3a6c3148491553ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a951e209131cea2911d.md>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### ELR+

Accuracy (Symmetric 20%): 95.8. Result ID: 69935a2e3a6c3148491553c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d383.md>)

[Implementation](<https://github.com/shengliu66/ELR>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":true}. This record does not assert independent reproduction.

### RRL

Accuracy (Symmetric 20%): 95.8. Result ID: 69935a2e3a6c3148491553c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### LossModelling

Accuracy (Symmetric 20%): 94. Result ID: 69935a2e3a6c3148491553c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65d71e209131cea0cad4.md>)

[Implementation](<https://git.io/fjsvE>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### PENCIL

Accuracy (Symmetric 20%): 92.4. Result ID: 69935a2e3a6c3148491553c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65801e209131cea0a8aa.md>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### Co-teaching+

Accuracy (Symmetric 20%): 89.5. Result ID: 69935a2e3a6c3148491553c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

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

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### Cross-Entropy

Accuracy (Symmetric 20%): 86.8. Result ID: 69935a2e3a6c3148491553c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

### F-correction

Accuracy (Symmetric 20%): 86.8. Result ID: 69935a2e3a6c3148491553c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea639e7.md>)

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

Recorded evaluation configuration: {"Advanced Training Config (SSL/Co-training/Pre-training)":false}. This record does not assert independent reproduction.

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