# Image Classification on CUB 200 2011 (Accuracy and Statistical Comparison)

Source: [Image Classification on CUB 200 2011 (Accuracy and Statistical Comparison)](<https://www.sota2.com/research/sota/image-classification-on-cub-200-2011-accuracy-and-statistical-comparison>)

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

Data updated: 2026-06-17T06:52:33.474Z

Evaluation of standard Image Classification performance on the CUB 200 2011 dataset, reporting primary accuracy alongside statistical comparison metrics like Wilcoxon p-value and Cohen's d effect size.

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) | CUB200 2011 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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-accuracy-and-statistical-comparison.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Relative Gain](<https://www.sota2.com/research/sota/image-classification-on-cub-200-2011-accuracy-and-statistical-comparison.md?metric=Relative%20Gain>): Higher is better; unit: PERCENT.

- [Wilcoxon p-value](<https://www.sota2.com/research/sota/image-classification-on-cub-200-2011-accuracy-and-statistical-comparison.md?metric=Wilcoxon%20p-value>): Lower is better; unit: SCALAR.

- [Cohen's d](<https://www.sota2.com/research/sota/image-classification-on-cub-200-2011-accuracy-and-statistical-comparison.md?metric=Cohen%27s%20d>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Multi-Feature Aggregation for GNNs | 83.33 | Not recorded | 6a322a36d33dfb23e783ec2f |
| SGC (SWIN-TF) | 82.05 | Not recorded | 6a322a36d33dfb23e783ec2f |

### Multi-Feature Aggregation for GNNs

Accuracy: 83.33. Result ID: 6a324418fbc373592c2f30d8.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a36d33dfb23e783ec2f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a36d33dfb23e783ec2f.md>)

Recorded evaluation configuration: {"Features":"VIT-B16","Graph":"SWIN-TF","M.L.":"RDPAC"}. This record does not assert independent reproduction.

### SGC (SWIN-TF)

Accuracy: 82.05. Result ID: 6a324418fbc373592c2f30d7.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a36d33dfb23e783ec2f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f61e209131cea0d766.md>)

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

Recorded evaluation configuration: {"Feature":"SWIN-TF","M.L.":"No Manifold Learning"}. This record does not assert independent reproduction.

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