# Image Classification on CUB-200-2011 (30% labels)

Source: [Image Classification on CUB-200-2011 (30% labels)](<https://www.sota2.com/research/sota/image-classification-on-cub-200-2011-30-percent-labels>)

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

Data updated: 2026-02-26T05:28:20.128Z

Evaluation of Image Classification performance on the CUB-200-2011 dataset using only 30% of the available 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) | CUB-200-2011 (30% labels) |
| 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-cub-200-2011-30-percent-labels.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Self-Tuning+HCR | 75.06 | Not recorded | 68fa6cb81e209131cea358e5 |
| Self-Tuning | 74.31 | Not recorded | 68fa6cb81e209131cea358e5 |
| Mean Teacher | 66.66 | Not recorded | 68fa6cb81e209131cea358e5 |
| FixMatch | 63.54 | Not recorded | 68fa6cb81e209131cea358e5 |
| SimCLRv2 | 62.7 | Not recorded | 68fa6cb81e209131cea358e5 |
| UDA | 61.16 | Not recorded | 68fa6cb81e209131cea358e5 |
| Π-model | 58.49 | Not recorded | 68fa6cb81e209131cea358e5 |
| Pseudo-Labeling | 56.2 | Not recorded | 68fa6cb81e209131cea358e5 |

### Self-Tuning+HCR

Accuracy: 75.06. Result ID: 698f35413a6c314849f70237.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

### Self-Tuning

Accuracy: 74.31. Result ID: 698f35413a6c314849f70236.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5e1e209131cea27c29.md>)

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

### Mean Teacher

Accuracy: 66.66. Result ID: 698f35413a6c314849f70232.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

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

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

### FixMatch

Accuracy: 63.54. Result ID: 698f35413a6c314849f70234.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

### SimCLRv2

Accuracy: 62.7. Result ID: 698f35413a6c314849f70235.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a21e209131cea1d4d1.md>)

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

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

### UDA

Accuracy: 61.16. Result ID: 698f35413a6c314849f70233.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

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

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

### Π-model

Accuracy: 58.49. Result ID: 698f35413a6c314849f70231.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

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

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

### Pseudo-Labeling

Accuracy: 56.2. Result ID: 698f35413a6c314849f70230.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea358e5.md>)

Recorded evaluation configuration: {"Network":"ResNet-50","Pre-trained":true,"Label Proportion":"30%"}. This record does not assert independent reproduction.

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