# Image Classification on CIFAR-10 4000-label (train test)

Source: [Image Classification on CIFAR-10 4000-label (train test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-4000-label-train-test>)

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

Data updated: 2026-02-26T05:52:31.254Z

Evaluation of Image Classification performance on a specific 4000-label subset of the CIFAR-10 dataset covering both training and testing splits, measured by Median error rate.

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 4000-label (train test) |
| Metric | Median Error Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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

- [Median Error Rate](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-4000-label-train-test.md?metric=Median%20Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Median Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| FixMatch | 4.46 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| FlexMatch | 4.47 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| Flex-UDA | 4.52 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| UDA | 4.6 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| Flex-PL | 15.3 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| PL | 15.64 | Not recorded | 68fa6bbb1e209131cea2ff1d |

### FixMatch

Median Error Rate: 4.46. Result ID: 698ea134ffc3901de09f46a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d61e209131cea1e896.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Label Amount":"4000"}. This record does not assert independent reproduction.

### FlexMatch

Median Error Rate: 4.47. Result ID: 698ea134ffc3901de09f46aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Label Amount":"4000"}. This record does not assert independent reproduction.

### Flex-UDA

Median Error Rate: 4.52. Result ID: 698ea134ffc3901de09f46a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Label Amount":"4000"}. This record does not assert independent reproduction.

### UDA

Median Error Rate: 4.6. Result ID: 698ea134ffc3901de09f46a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a61e209131cea1d69a.md>)

[Implementation](<https://github.com/google-research/uda>)

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Label Amount":"4000"}. This record does not assert independent reproduction.

### Flex-PL

Median Error Rate: 15.3. Result ID: 698ea134ffc3901de09f46a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Label Amount":"4000"}. This record does not assert independent reproduction.

### PL

Median Error Rate: 15.64. Result ID: 698ea134ffc3901de09f46a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Label Amount":"4000"}. This record does not assert independent reproduction.

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