# Image Classification on SVHN 1,000 labels (train)

Source: [Image Classification on SVHN 1,000 labels (train)](<https://www.sota2.com/research/sota/image-classification-on-svhn-1-000-labels-train>)

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

Data updated: 2026-02-26T05:42:20.954Z

Evaluation of Image Classification performance on the training split of the 1,000-label subset of the SVHN dataset.

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 1,000 labels (train) |
| Metric | Error Rate (%) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 15 of 15 |
| 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-svhn-1-000-labels-train.md?metric=Error%20Rate%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Error Rate (%) | Result date | Report paper |
| --- | --- | --- | --- |
| Triple-GAN-V2 | 3.96 | Not recorded | 68fa68521e209131cea1b71b |
| SNTG | 4.02 | Not recorded | 68fa68521e209131cea1b71b |
| BadGAN | 4.25 | Not recorded | 68fa68521e209131cea1b71b |
| VAT+Ent | 4.28 | Not recorded | 68fa68521e209131cea1b71b |
| MMCVA | 4.95 | Not recorded | 68fa68521e209131cea1b71b |
| MT | 5.21 | Not recorded | 68fa68521e209131cea1b71b |
| MT (our code base) | 5.39 | Not recorded | 68fa68521e209131cea1b71b |
| Π model | 5.73 | Not recorded | 68fa68521e209131cea1b71b |
| Triple-GAN-V1 | 5.77 | Not recorded | 68fa68521e209131cea1b71b |
| VAT | 5.77 | Not recorded | 68fa68521e209131cea1b71b |
| Pseudo Label | 7.62 | Not recorded | 68fa68521e209131cea1b71b |
| Improved-GAN | 8.11 | Not recorded | 68fa68521e209131cea1b71b |
| SDGM | 16.61 | Not recorded | 68fa68521e209131cea1b71b |
| ADGM | 22.86 | Not recorded | 68fa68521e209131cea1b71b |
| M1+M2 | 36.02 | Not recorded | 68fa68521e209131cea1b71b |

### Triple-GAN-V2

Error Rate (%): 3.96. Result ID: 698d6a808b517eb433215701.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Implementation](<https://github.com/zhenxuan00/triple-gan>)

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN (classifier in \[32\])"}. This record does not assert independent reproduction.

### SNTG

Error Rate (%): 4.02. Result ID: 698d6a808b517eb4332156fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642f1e209131cea0344b.md>)

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN"}. This record does not assert independent reproduction.

### BadGAN

Error Rate (%): 4.25. Result ID: 698d6a808b517eb4332156f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

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

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN"}. This record does not assert independent reproduction.

### VAT+Ent

Error Rate (%): 4.28. Result ID: 698d6a808b517eb4332156fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

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

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN"}. This record does not assert independent reproduction.

### MMCVA

Error Rate (%): 4.95. Result ID: 698d6a808b517eb4332156f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63001e209131ce9fc357.md>)

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Extra Unlabeled Data":true}. This record does not assert independent reproduction.

### MT

Error Rate (%): 5.21. Result ID: 698d6a808b517eb4332156ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

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

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN"}. This record does not assert independent reproduction.

### MT (our code base)

Error Rate (%): 5.39. Result ID: 698d6a808b517eb433215700.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

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

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN (classifier in \[32\])"}. This record does not assert independent reproduction.

### Π model

Error Rate (%): 5.73. Result ID: 698d6a808b517eb4332156fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN"}. This record does not assert independent reproduction.

### Triple-GAN-V1

Error Rate (%): 5.77. Result ID: 698d6a808b517eb4332156f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Implementation](<https://github.com/zhenxuan00/triple-gan>)

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN (classifier in \[26\])"}. This record does not assert independent reproduction.

### VAT

Error Rate (%): 5.77. Result ID: 698d6a808b517eb4332156fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

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

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN"}. This record does not assert independent reproduction.

### Pseudo Label

Error Rate (%): 7.62. Result ID: 698d6a808b517eb4332156fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65de1e209131cea0cf4b.md>)

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN"}. This record does not assert independent reproduction.

### Improved-GAN

Error Rate (%): 8.11. Result ID: 698d6a808b517eb4332156f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62821e209131ce9f9b67.md>)

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Classifier":"13-layer CNN (classifier in \[26\])"}. This record does not assert independent reproduction.

### SDGM

Error Rate (%): 16.61. Result ID: 698d6a808b517eb4332156f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62831e209131ce9f9c5e.md>)

[Implementation](<https://www.sota2.com/github.com/auxiliary-deep-generative-models>)

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Extra Unlabeled Data":true}. This record does not assert independent reproduction.

### ADGM

Error Rate (%): 22.86. Result ID: 698d6a808b517eb4332156f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62831e209131ce9f9c5e.md>)

[Implementation](<https://www.sota2.com/github.com/auxiliary-deep-generative-models>)

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false,"Extra Unlabeled Data":true}. This record does not assert independent reproduction.

### M1+M2

Error Rate (%): 36.02. Result ID: 698d6a808b517eb4332156f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68521e209131cea1b71b.md>)

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

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

Recorded evaluation configuration: {"Number of labels":1000,"Data Augmentation":false}. This record does not assert independent reproduction.

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