# Image Classification on CIFAR-10 RST 500K-unlabeled (test)

Source: [Image Classification on CIFAR-10 RST 500K-unlabeled (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-rst-500k-unlabeled-test>)

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

Data updated: 2026-06-04T10:12:41.136Z

Evaluation of Image Classification performance on the CIFAR-10 dataset using the specific RST 500K unlabeled test split, reporting Clean Accuracy, Average Accuracy (AA), and performance Gap metrics.

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 RST 500K-unlabeled (test) |
| Metric | Clean 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

- [Clean Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-rst-500k-unlabeled-test.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy (AA)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-rst-500k-unlabeled-test.md?metric=Average%20Accuracy%20(AA)>): Higher is better; unit: PERCENT.

- [Performance Gap](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-rst-500k-unlabeled-test.md?metric=Performance%20Gap>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Clean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HICAT | 89.1 | Not recorded | 6a210694c10484bac23f01f4 |
| DHAT | 88.45 | Not recorded | 6a210694c10484bac23f01f4 |
| SGLR | 88.25 | Not recorded | 6a210694c10484bac23f01f4 |
| UIAT | 87.25 | Not recorded | 6a210694c10484bac23f01f4 |
| CFA | 86.3 | Not recorded | 6a210694c10484bac23f01f4 |
| MART | 84.7 | Not recorded | 6a210694c10484bac23f01f4 |
| AWP | 84.6 | Not recorded | 6a210694c10484bac23f01f4 |
| FSR | 84.4 | Not recorded | 6a210694c10484bac23f01f4 |

### HICAT

Clean Accuracy: 89.1. Result ID: 6a214f89fbc373592c1d8c4b.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

### DHAT

Clean Accuracy: 88.45. Result ID: 6a214f89fbc373592c1d8c4a.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79f41e209131cea803d5.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

### SGLR

Clean Accuracy: 88.25. Result ID: 6a214f89fbc373592c1d8c49.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727d1e209131cea56b56.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

### UIAT

Clean Accuracy: 87.25. Result ID: 6a214f89fbc373592c1d8c48.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dd31e209131cea3c391.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

### CFA

Clean Accuracy: 86.3. Result ID: 6a214f89fbc373592c1d8c47.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee91e209131cea42dc7.md>)

[Implementation](<https://github.com/PKU-ML/CFA>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

### MART

Clean Accuracy: 84.7. Result ID: 6a214f89fbc373592c1d8c44.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

### AWP

Clean Accuracy: 84.6. Result ID: 6a214f89fbc373592c1d8c45.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa687e1e209131cea1c519.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

### FSR

Clean Accuracy: 84.4. Result ID: 6a214f89fbc373592c1d8c46.

[Reporting paper](<https://www.sota2.com/research/paper/6a210694c10484bac23f01f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee61e209131cea42bf0.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-10","Semi-supervised":"true","Unlabeled data":"RST 500K"}. This record does not assert independent reproduction.

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