# Personalized Image Classification on CIFAR-10 Dirichlet 0.5 (test)

Source: [Personalized Image Classification on CIFAR-10 Dirichlet 0.5 (test)](<https://www.sota2.com/research/sota/personalized-image-classification-on-cifar-10-dirichlet-0-5-test>)

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

Data updated: 2026-02-26T05:57:58.910Z

Evaluation of Personalized Image Classification performance on the CIFAR-10 dataset partitioned using a Dirichlet non-IID distribution setting with alpha=0.5, measured on the test set.

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 | Personalized Image Classification |
| Dataset (including any stated split) | CIFAR-10 Dirichlet 0.5 (test) |
| Metric | Personalized 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

- [Personalized Accuracy](<https://www.sota2.com/research/sota/personalized-image-classification-on-cifar-10-dirichlet-0-5-test.md?metric=Personalized%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Personalized Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FedPAC | 79.47 | Not recorded | 68fa755d1e209131cea6780b |
| Ditto | 79.2 | Not recorded | 68fa755d1e209131cea6780b |
| FedCCFA-FT | 79.13 | Not recorded | 68fa755d1e209131cea6780b |
| FedCCFA | 75.03 | Not recorded | 68fa755d1e209131cea6780b |
| FedBABU | 71.29 | Not recorded | 68fa755d1e209131cea6780b |
| FedRep | 68.85 | Not recorded | 68fa755d1e209131cea6780b |
| pFedMe | 60.42 | Not recorded | 68fa755d1e209131cea6780b |

### FedPAC

Personalized Accuracy: 79.47. Result ID: 6993ab633a6c31484917b03f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea4759f.md>)

Recorded evaluation configuration: {"Participation rate":"20%","Number of clients":"100","Drift setting":"no drift"}. This record does not assert independent reproduction.

### Ditto

Personalized Accuracy: 79.2. Result ID: 6993ab633a6c31484917b03c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2d1e209131cea269df.md>)

Recorded evaluation configuration: {"Participation rate":"20%","Number of clients":"100","Drift setting":"no drift"}. This record does not assert independent reproduction.

### FedCCFA-FT

Personalized Accuracy: 79.13. Result ID: 6993ab633a6c31484917b041.

[Reporting paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Implementation](<https://github.com/Chen-Junbao/FedCCFA>)

Recorded evaluation configuration: {"Participation rate":"20%","Number of clients":"100","Drift setting":"no drift","Fine-tuning":"5 epochs","Fine-tuning learning rate":0.01}. This record does not assert independent reproduction.

### FedCCFA

Personalized Accuracy: 75.03. Result ID: 6993ab633a6c31484917b040.

[Reporting paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Implementation](<https://github.com/Chen-Junbao/FedCCFA>)

Recorded evaluation configuration: {"Participation rate":"20%","Number of clients":"100","Drift setting":"no drift","Fine-tuning":false}. This record does not assert independent reproduction.

### FedBABU

Personalized Accuracy: 71.29. Result ID: 6993ab633a6c31484917b03e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfa1e209131cea31630.md>)

Recorded evaluation configuration: {"Participation rate":"20%","Number of clients":"100","Drift setting":"no drift"}. This record does not assert independent reproduction.

### FedRep

Personalized Accuracy: 68.85. Result ID: 6993ab633a6c31484917b03d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5a3d1e209131ce9be169.md>)

Recorded evaluation configuration: {"Participation rate":"20%","Number of clients":"100","Drift setting":"no drift"}. This record does not assert independent reproduction.

### pFedMe

Personalized Accuracy: 60.42. Result ID: 6993ab633a6c31484917b03b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa755d1e209131cea6780b.md>)

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

Recorded evaluation configuration: {"Participation rate":"20%","Number of clients":"100","Drift setting":"no drift"}. This record does not assert independent reproduction.

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