# Image Classification on STL-10 USB (40 labels)

Source: [Image Classification on STL-10 USB (40 labels)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-usb-40-labels>)

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

Data updated: 2026-02-26T05:42:18.194Z

Image Classification performance evaluation using the 40-label subset of the STL-10 USB dataset, reporting 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) | STL-10 USB (40 labels) |
| Metric | Error Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 14 of 14 |
| 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](<https://www.sota2.com/research/sota/image-classification-on-stl-10-usb-40-labels.md?metric=Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| ILL | 11.09 | Not recorded | 68fa75781e209131cea682ff |
| SimMatch | 11.77 | Not recorded | 68fa75781e209131cea682ff |
| FreeMatch | 12.73 | Not recorded | 68fa75781e209131cea682ff |
| ReMixMatch | 13.08 | Not recorded | 68fa75781e209131cea682ff |
| SoftMatch | 13.55 | Not recorded | 68fa75781e209131cea682ff |
| AdaMatch | 13.64 | Not recorded | 68fa75781e209131cea682ff |
| FlexMatch | 14.4 | Not recorded | 68fa75781e209131cea682ff |
| CoMatch | 15.12 | Not recorded | 68fa75781e209131cea682ff |
| FixMatch | 16.15 | Not recorded | 68fa75781e209131cea682ff |
| Dash | 16.22 | Not recorded | 68fa75781e209131cea682ff |
| VAT | 18.45 | Not recorded | 68fa75781e209131cea682ff |
| Mean-Teacher | 18.67 | Not recorded | 68fa75781e209131cea682ff |
| Pseudo-Label | 19.14 | Not recorded | 68fa75781e209131cea682ff |
| MixMatch | 58.77 | Not recorded | 68fa75781e209131cea682ff |

### ILL

Error Rate: 11.09. Result ID: 6993b3b23a6c31484917ee86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### SimMatch

Error Rate: 11.77. Result ID: 6993b3b23a6c31484917ee83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### FreeMatch

Error Rate: 12.73. Result ID: 6993b3b23a6c31484917ee84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### ReMixMatch

Error Rate: 13.08. Result ID: 6993b3b23a6c31484917ee7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### SoftMatch

Error Rate: 13.55. Result ID: 6993b3b23a6c31484917ee85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### AdaMatch

Error Rate: 13.64. Result ID: 6993b3b23a6c31484917ee7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### FlexMatch

Error Rate: 14.4. Result ID: 6993b3b23a6c31484917ee80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### CoMatch

Error Rate: 15.12. Result ID: 6993b3b23a6c31484917ee82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### FixMatch

Error Rate: 16.15. Result ID: 6993b3b23a6c31484917ee7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### Dash

Error Rate: 16.22. Result ID: 6993b3b23a6c31484917ee81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### VAT

Error Rate: 18.45. Result ID: 6993b3b23a6c31484917ee7b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64891e209131cea054b5.md>)

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### Mean-Teacher

Error Rate: 18.67. Result ID: 6993b3b23a6c31484917ee7a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b45.md>)

[Implementation](<https://github.com/CuriousAI/mean-teacher>)

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### Pseudo-Label

Error Rate: 19.14. Result ID: 6993b3b23a6c31484917ee79.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

### MixMatch

Error Rate: 58.77. Result ID: 6993b3b23a6c31484917ee7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ff.md>)

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

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

Recorded evaluation configuration: {"# Labels":"40","Evaluation protocol":"Average of 3 independent runs"}. This record does not assert independent reproduction.

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