# Semi-supervised Image Classification on CIFAR10 80 labels (0.16%) (test)

Source: [Semi-supervised Image Classification on CIFAR10 80 labels (0.16%) (test)](<https://www.sota2.com/research/sota/semi-supervised-image-classification-on-cifar10-80-labels-0-16-percent-test>)

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

Data updated: 2026-02-26T05:28:15.275Z

Evaluation of Semi-supervised Image Classification performance on the CIFAR-10 test split using only 80 labeled examples (0.16% supervision).

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 80 labels (0.16%) (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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-cifar10-80-labels-0-16-percent-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DebiasPL (w/ FixMatch) | 95.2 | Not recorded | 68fa6c551e209131cea33540 |
| CoMatch w/ SimCLR | 94 | Not recorded | 68fa6c551e209131cea33540 |
| FixMatch w/ DA w/ SimCLR | 93.3 | Not recorded | 68fa6c551e209131cea33540 |
| FixMatch | 92.1 | Not recorded | 68fa6c551e209131cea33540 |
| MixMatch | 80.8 | Not recorded | 68fa6c551e209131cea33540 |

### DebiasPL (w/ FixMatch)

Accuracy: 95.2. Result ID: 698f033e3a6c314849f4c489.

[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"}. This record does not assert independent reproduction.

### CoMatch w/ SimCLR

Accuracy: 94. Result ID: 698f033e3a6c314849f4c486.

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

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

### FixMatch w/ DA w/ SimCLR

Accuracy: 93.3. Result ID: 698f033e3a6c314849f4c488.

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

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

### FixMatch

Accuracy: 92.1. Result ID: 698f033e3a6c314849f4c487.

[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"}. This record does not assert independent reproduction.

### MixMatch

Accuracy: 80.8. Result ID: 698f033e3a6c314849f4c485.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa66961e209131cea11261.md>)

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

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

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