# Image Classification on SVHN 1k labeled 72k unlabeled (test)

Source: [Image Classification on SVHN 1k labeled 72k unlabeled (test)](<https://www.sota2.com/research/sota/image-classification-on-svhn-1k-labeled-72k-unlabeled-test>)

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

Data updated: 2026-02-26T05:27:35.649Z

Evaluation of Image Classification performance on the SVHN test set subset containing 1000 labeled examples and 72k unlabeled examples.

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) | SVHN 1k labeled 72k unlabeled (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/image-classification-on-svhn-1k-labeled-72k-unlabeled-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FlowGMM Sup | 95.81 | Not recorded | 68fa66e61e209131cea12fb6 |
| BadGAN | 95.75 | Not recorded | 68fa66e61e209131cea12fb6 |
| DIGLM Sup | 95.74 | Not recorded | 68fa66e61e209131cea12fb6 |
| Π-Model | 94.57 | Not recorded | 68fa66e61e209131cea12fb6 |
| FlowGMM-cons | 86.44 | Not recorded | 68fa66e61e209131cea12fb6 |
| FlowGMM | 82.42 | Not recorded | 68fa66e61e209131cea12fb6 |
| FlowGMM Sup | 78.26 | Not recorded | 68fa66e61e209131cea12fb6 |
| M1+M2 VAE SSL | 63.98 | Not recorded | 68fa66e61e209131cea12fb6 |

### FlowGMM Sup

Accuracy: 95.81. Result ID: 698d0efc8b517eb4331eac8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

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

Recorded evaluation configuration: {"Training Labels":"All labels","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### BadGAN

Accuracy: 95.75. Result ID: 698d0efc8b517eb4331eac94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63bc1e209131cea0080d.md>)

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

Recorded evaluation configuration: {"Learning Paradigm":"Semi-supervised"}. This record does not assert independent reproduction.

### DIGLM Sup

Accuracy: 95.74. Result ID: 698d0efc8b517eb4331eac8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65da1e209131cea0cc89.md>)

Recorded evaluation configuration: {"Training Labels":"All labels","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### Π-Model

Accuracy: 94.57. Result ID: 698d0efc8b517eb4331eac95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63301e209131ce9fd2e9.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Semi-supervised"}. This record does not assert independent reproduction.

### FlowGMM-cons

Accuracy: 86.44. Result ID: 698d0efc8b517eb4331eac93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

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

Recorded evaluation configuration: {"Learning Paradigm":"Semi-supervised","Consistency Regularization":"true"}. This record does not assert independent reproduction.

### FlowGMM

Accuracy: 82.42. Result ID: 698d0efc8b517eb4331eac92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

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

Recorded evaluation configuration: {"Learning Paradigm":"Semi-supervised"}. This record does not assert independent reproduction.

### FlowGMM Sup

Accuracy: 78.26. Result ID: 698d0efc8b517eb4331eac91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

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

Recorded evaluation configuration: {"Training Labels":"ni labels","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### M1+M2 VAE SSL

Accuracy: 63.98. Result ID: 698d0efc8b517eb4331eac90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea12fb6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa619a1e209131ce9f5097.md>)

[Implementation](<http://github.com/dpkingma/nips14-ssl>)

Recorded evaluation configuration: {"Learning Paradigm":"Semi-supervised"}. This record does not assert independent reproduction.

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