# Image Classification on CIFAR-100 400-label (train test)

Source: [Image Classification on CIFAR-100 400-label (train test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-400-label-train-test>)

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

Data updated: 2026-02-26T05:52:31.268Z

Evaluation of Image Classification performance on the CIFAR-100 dataset, specifically using the subset defined by 400 labels per class across the combined train and test splits.

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-100 400-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-100-400-label-train-test.md?metric=Median%20Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Median Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| FlexMatch | 45.91 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| FixMatch | 48.95 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| UDA | 51.97 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| Flex-UDA | 59.51 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| Flex-PL | 86.6 | Not recorded | 68fa6bbb1e209131cea2ff1d |
| PL | 90.01 | Not recorded | 68fa6bbb1e209131cea2ff1d |

### FlexMatch

Median Error Rate: 45.91. Result ID: 698ea134ffc3901de09f46b0.

[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-28-8","Label Amount":"400"}. This record does not assert independent reproduction.

### FixMatch

Median Error Rate: 48.95. Result ID: 698ea134ffc3901de09f46af.

[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-28-8","Label Amount":"400"}. This record does not assert independent reproduction.

### UDA

Median Error Rate: 51.97. Result ID: 698ea134ffc3901de09f46ad.

[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-28-8","Label Amount":"400"}. This record does not assert independent reproduction.

### Flex-UDA

Median Error Rate: 59.51. Result ID: 698ea134ffc3901de09f46ae.

[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-28-8","Label Amount":"400"}. This record does not assert independent reproduction.

### Flex-PL

Median Error Rate: 86.6. Result ID: 698ea134ffc3901de09f46ac.

[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-28-8","Label Amount":"400"}. This record does not assert independent reproduction.

### PL

Median Error Rate: 90.01. Result ID: 698ea134ffc3901de09f46ab.

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

Recorded evaluation configuration: {"Backbone":"WRN-28-8","Label Amount":"400"}. This record does not assert independent reproduction.

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