# Image Classification on CIFAR-100 Dirichlet (Varying Beta) (test)

Source: [Image Classification on CIFAR-100 Dirichlet (Varying Beta) (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-dirichlet-varying-beta-test>)

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

Data updated: 2026-02-26T05:34:31.185Z

Evaluation of Image Classification performance on the test split of CIFAR-100 under various non-IID settings defined by the Dirichlet distribution parameter β (e.g., β=0.1, 0.3, 0.5).

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) | CIFAR-100 Dir(beta) (test) |
| Metric | Accuracy (beta=0.5) |
| 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 (beta=0.5)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-dirichlet-varying-beta-test.md?metric=Accuracy%20(beta%3D0.5)>): Higher is better; unit: PERCENT.

- [Accuracy (beta=0.3)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-dirichlet-varying-beta-test.md?metric=Accuracy%20(beta%3D0.3)>): Higher is better; unit: PERCENT.

- [Accuracy (beta=0.1)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-dirichlet-varying-beta-test.md?metric=Accuracy%20(beta%3D0.1)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (beta=0.5) | Result date | Report paper |
| --- | --- | --- | --- |
| FedAvg (CoOp) + GGTPC | 84.21 | Not recorded | 6937ad546cfd488761a4ec46 |
| FedVPT | 83.53 | Not recorded | 6937ad546cfd488761a4ec46 |
| FedPR | 81.17 | Not recorded | 6937ad546cfd488761a4ec46 |
| FedAvg (CoOp) | 79.28 | Not recorded | 6937ad546cfd488761a4ec46 |
| PromptFL | 75.05 | Not recorded | 6937ad546cfd488761a4ec46 |
| FedCLIP | 72.03 | Not recorded | 6937ad546cfd488761a4ec46 |
| FedTPG | 71.4 | Not recorded | 6937ad546cfd488761a4ec46 |
| Zero-shot CLIP | 64.87 | Not recorded | 6937ad546cfd488761a4ec46 |

### FedAvg (CoOp) + GGTPC

Accuracy (beta=0.5): 84.21. Result ID: 69997d2d5698665ec4ecbd49.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

Recorded evaluation configuration: {"Backbone":"CoOp","Evaluation Protocol":"Federated Learning","Module":"GGTPC"}. This record does not assert independent reproduction.

### FedVPT

Accuracy (beta=0.5): 83.53. Result ID: 69997d2d5698665ec4ecbd43.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d181e209131cea37ae9.md>)

[Implementation](<https://www.sota2.com/github.com/kmnp/vpt>)

Recorded evaluation configuration: {"Evaluation Protocol":"Federated Learning"}. This record does not assert independent reproduction.

### FedPR

Accuracy (beta=0.5): 81.17. Result ID: 69997d2d5698665ec4ecbd46.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42b07.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Federated Learning"}. This record does not assert independent reproduction.

### FedAvg (CoOp)

Accuracy (beta=0.5): 79.28. Result ID: 69997d2d5698665ec4ecbd48.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8b1e209131cea3a814.md>)

[Implementation](<https://github.com/KaiyangZhou/CoOp>)

Recorded evaluation configuration: {"Backbone":"CoOp","Evaluation Protocol":"Federated Learning"}. This record does not assert independent reproduction.

### PromptFL

Accuracy (beta=0.5): 75.05. Result ID: 69997d2d5698665ec4ecbd44.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d511e209131cea391ba.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Federated Learning"}. This record does not assert independent reproduction.

### FedCLIP

Accuracy (beta=0.5): 72.03. Result ID: 69997d2d5698665ec4ecbd47.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ffb1e209131cea484b1.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Federated Learning"}. This record does not assert independent reproduction.

### FedTPG

Accuracy (beta=0.5): 71.4. Result ID: 69997d2d5698665ec4ecbd45.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Federated Learning"}. This record does not assert independent reproduction.

### Zero-shot CLIP

Accuracy (beta=0.5): 64.87. Result ID: 69997d2d5698665ec4ecbd42.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

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