# Image Classification on STL-10 (Label Count Specific Error Rates)

Source: [Image Classification on STL-10 (Label Count Specific Error Rates)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-label-count-specific-error-rates>)

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

Data updated: 2026-02-26T05:42:21.777Z

Evaluation of Image Classification performance on the STL-10 dataset, reporting error rates derived from specific subsets of 40, 250, and 1000 labels.

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) | STL-10 |
| Metric | Error Rate (40 Labels) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| 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

- [Error Rate (40 Labels)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-label-count-specific-error-rates.md?metric=Error%20Rate%20(40%20Labels)>): Lower is better; unit: PERCENT.

- [Error Rate (250 Labels)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-label-count-specific-error-rates.md?metric=Error%20Rate%20(250%20Labels)>): Lower is better; unit: PERCENT.

- [Error Rate (1000 Labels)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-label-count-specific-error-rates.md?metric=Error%20Rate%20(1000%20Labels)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Error Rate (40 Labels) | Result date | Report paper |
| --- | --- | --- | --- |
| CoMatch + EPASS | 9.15 | Not recorded | 68fa70f11e209131cea4e324 |
| CoMatch | 13.74 | Not recorded | 68fa70f11e209131cea4e324 |
| SimMatch + EPASS | 15.71 | Not recorded | 68fa70f11e209131cea4e324 |
| SimMatch | 16.98 | Not recorded | 68fa70f11e209131cea4e324 |
| AdaMatch | 19.95 | Not recorded | 68fa70f11e209131cea4e324 |
| SoftMatch | 22.23 | Not recorded | 68fa70f11e209131cea4e324 |
| ReMixMatch | 27.87 | Not recorded | 68fa70f11e209131cea4e324 |
| FreeMatch | 28.5 | Not recorded | 68fa70f11e209131cea4e324 |
| FlexMatch | 29.12 | Not recorded | 68fa70f11e209131cea4e324 |
| FixMatch | 38.19 | Not recorded | 68fa70f11e209131cea4e324 |
| Dash | 42 | Not recorded | 68fa70f11e209131cea4e324 |
| MixMatch | 52.32 | Not recorded | 68fa70f11e209131cea4e324 |
| UDA | 53.69 | Not recorded | 68fa70f11e209131cea4e324 |

### CoMatch + EPASS

Error Rate (40 Labels): 9.15. Result ID: 699165213a6c31484907db38.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CoMatch

Error Rate (40 Labels): 13.74. Result ID: 699165213a6c31484907db33.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69751e209131cea2238f.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SimMatch + EPASS

Error Rate (40 Labels): 15.71. Result ID: 699165213a6c31484907db39.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SimMatch

Error Rate (40 Labels): 16.98. Result ID: 699165213a6c31484907db34.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0c1e209131cea31a70.md>)

[Implementation](<https://github.com/KyleZheng1997/simmatch>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AdaMatch

Error Rate (40 Labels): 19.95. Result ID: 699165213a6c31484907db35.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c011e209131cea319a6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SoftMatch

Error Rate (40 Labels): 22.23. Result ID: 699165213a6c31484907db37.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ec31e209131cea41dad.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ReMixMatch

Error Rate (40 Labels): 27.87. Result ID: 699165213a6c31484907db2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FreeMatch

Error Rate (40 Labels): 28.5. Result ID: 699165213a6c31484907db36.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e711e209131cea3fd15.md>)

[Implementation](<https://github.com/microsoft/Semi-supervised-learning>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FlexMatch

Error Rate (40 Labels): 29.12. Result ID: 699165213a6c31484907db31.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FixMatch

Error Rate (40 Labels): 38.19. Result ID: 699165213a6c31484907db30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Dash

Error Rate (40 Labels): 42. Result ID: 699165213a6c31484907db32.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aa61e209131cea2970c.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MixMatch

Error Rate (40 Labels): 52.32. Result ID: 699165213a6c31484907db2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### UDA

Error Rate (40 Labels): 53.69. Result ID: 699165213a6c31484907db2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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