# Semi-supervised Image Classification on CIFAR10-LT gamma=200, 3365 labels (30%) (test)

Source: [Semi-supervised Image Classification on CIFAR10-LT gamma=200, 3365 labels (30%) (test)](<https://www.sota2.com/research/sota/semi-supervised-image-classification-on-cifar10-lt-gamma-200-3365-labels-30-percent-test>)

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

Data updated: 2026-02-26T05:28:15.238Z

Evaluation of Semi-supervised Image Classification performance on the CIFAR-10 Long-Tailed dataset variant configured with gamma=200 and exactly 3365 labels (30% imbalance), tested on the test split.

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 | Semi-supervised Image Classification |
| Dataset (including any stated split) | CIFAR10-LT gamma=200, 3365 labels (30%) (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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](<https://www.sota2.com/research/sota/semi-supervised-image-classification-on-cifar10-lt-gamma-200-3365-labels-30-percent-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DebiasPL (w/ FixMatch) | 74.1 | Not recorded | 68fa6c551e209131cea33540 |
| CReST+ w/ DA | 70.5 | Not recorded | 68fa6c551e209131cea33540 |
| CReST w/ DA | 67.7 | Not recorded | 68fa6c551e209131cea33540 |
| FixMatch | 67.7 | Not recorded | 68fa6c551e209131cea33540 |

### DebiasPL (w/ FixMatch)

Accuracy: 74.1. Result ID: 698f033e3a6c314849f4c47e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c551e209131cea33540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c551e209131cea33540.md>)

[Implementation](<https://github.com/frank-xwang/debiased-pseudo-labeling>)

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Imbalance Ratio (gamma)":200}. This record does not assert independent reproduction.

### CReST+ w/ DA

Accuracy: 70.5. Result ID: 698f033e3a6c314849f4c47c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c551e209131cea33540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea26638.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Imbalance Ratio (gamma)":200}. This record does not assert independent reproduction.

### CReST w/ DA

Accuracy: 67.7. Result ID: 698f033e3a6c314849f4c47b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c551e209131cea33540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea26638.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Imbalance Ratio (gamma)":200}. This record does not assert independent reproduction.

### FixMatch

Accuracy: 67.7. Result ID: 698f033e3a6c314849f4c47d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c551e209131cea33540.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN-28-2","Imbalance Ratio (gamma)":200}. This record does not assert independent reproduction.

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