# Image Classification on Tiny ImageNet 1,000 labels (train)

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

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

Data updated: 2026-02-26T05:42:15.298Z

Evaluation of Image Classification performance on the training split of the Tiny ImageNet dataset, specifically using the 1,000 label subset, measured by 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) | Tiny ImageNet 1,000 labels (train) |
| Metric | Error Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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-tiny-imagenet-1-000-labels-train.md?metric=Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Triple-GAN-V2 | 17.4 | Not recorded | 68fa68521e209131cea1b71b |
| MT (our code base) | 20.67 | Not recorded | 68fa68521e209131cea1b71b |
| Triple-GAN-V1 | 24.83 | Not recorded | 68fa68521e209131cea1b71b |
| Improved-GAN | 28.47 | Not recorded | 68fa68521e209131cea1b71b |

### Triple-GAN-V2

Error Rate: 17.4. Result ID: 698d6a808b517eb43321571c.

[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.

### MT (our code base)

Error Rate: 20.67. Result ID: 698d6a808b517eb43321571b.

[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.

### Triple-GAN-V1

Error Rate: 24.83. Result ID: 698d6a808b517eb43321571a.

[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.

### Improved-GAN

Error Rate: 28.47. Result ID: 698d6a808b517eb433215719.

[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.

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