# Image Classification on CIFAR10 33 (test)

Source: [Image Classification on CIFAR10 33 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-33-test>)

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

Data updated: 2026-02-26T05:36:03.827Z

Evaluation of Image Classification performance on the CIFAR10 33 (test) split, measured using Average Accuracy and Bottom Decile Accuracy.

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) | CIFAR10 33 (test) |
| Metric | Avg Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Avg Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar10-33-test.md?metric=Avg%20Accuracy>): Higher is better; unit: PERCENT.

- [Bottom Decile Acc](<https://www.sota2.com/research/sota/image-classification-on-cifar10-33-test.md?metric=Bottom%20Decile%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FedEM | 84.3 | Not recorded | 68fa59bf1e209131ce9b9daf |
| FedAvg+ | 82.3 | Not recorded | 68fa59bf1e209131ce9b9daf |
| pFedMe | 81.7 | Not recorded | 68fa59bf1e209131ce9b9daf |
| Clustered FL | 78.6 | Not recorded | 68fa59bf1e209131ce9b9daf |
| FedAvg | 78.2 | Not recorded | 68fa59bf1e209131ce9b9daf |
| FedProx | 78 | Not recorded | 68fa59bf1e209131ce9b9daf |
| Local | 70.2 | Not recorded | 68fa59bf1e209131ce9b9daf |

### FedEM

Avg Accuracy: 84.3. Result ID: 698ba8a77a967eddb7706324.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

[Implementation](<https://github.com/omarfoq/FedEM>)

Recorded evaluation configuration: {"Model":"MobileNet-v2","M":3}. This record does not assert independent reproduction.

### FedAvg+

Avg Accuracy: 82.3. Result ID: 698ba8a77a967eddb7706321.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e641e209131cea3fa20.md>)

Recorded evaluation configuration: {"Model":"MobileNet-v2"}. This record does not assert independent reproduction.

### pFedMe

Avg Accuracy: 81.7. Result ID: 698ba8a77a967eddb7706323.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ba21e209131cea2f6fd.md>)

Recorded evaluation configuration: {"Model":"MobileNet-v2"}. This record does not assert independent reproduction.

### Clustered FL

Avg Accuracy: 78.6. Result ID: 698ba8a77a967eddb7706322.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66761e209131cea1046c.md>)

Recorded evaluation configuration: {"Model":"MobileNet-v2"}. This record does not assert independent reproduction.

### FedAvg

Avg Accuracy: 78.2. Result ID: 698ba8a77a967eddb770631f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e761e209131cea40072.md>)

Recorded evaluation configuration: {"Model":"MobileNet-v2"}. This record does not assert independent reproduction.

### FedProx

Avg Accuracy: 78. Result ID: 698ba8a77a967eddb7706320.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67701e209131cea163fe.md>)

Recorded evaluation configuration: {"Model":"MobileNet-v2"}. This record does not assert independent reproduction.

### Local

Avg Accuracy: 70.2. Result ID: 698ba8a77a967eddb770631e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59bf1e209131ce9b9daf.md>)

Recorded evaluation configuration: {"Model":"MobileNet-v2"}. This record does not assert independent reproduction.

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