# Image Classification on CIFAR100 (test) (Accuracy and Communication Floats to 45%)

Source: [Image Classification on CIFAR100 (test) (Accuracy and Communication Floats to 45%)](<https://www.sota2.com/research/sota/image-classification-on-cifar100-test-accuracy-and-communication-floats-to-45-percent>)

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

Data updated: 2026-03-06T09:18:55.433Z

Evaluation of Image Classification performance on the CIFAR-100 test set, reporting standard accuracy alongside the communication cost (in floats) required to achieve 45% 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) | CIFAR100 (test) |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar100-test-accuracy-and-communication-floats-to-45-percent.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Communication Floats (to 45% Acc)](<https://www.sota2.com/research/sota/image-classification-on-cifar100-test-accuracy-and-communication-floats-to-45-percent.md?metric=Communication%20Floats%20(to%2045%25%20Acc)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FedBCGD+ | 59.9 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedBCGD | 59.5 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedAdam | 49.9 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedAvgM | 48.3 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedDC | 46.6 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedAvg | 45.8 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| SCAFFOLD | 44.3 | Not recorded | 69aa5f8f2d603e6de3e41917 |

### FedBCGD+

Accuracy: 59.9. Result ID: 69aa9ba66dbb7075b95497c3.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

Recorded evaluation configuration: {"Heterogeneity (rho)":"0.1","Total communication floats":"1000d","Backbone":"ResNet-18","Number of blocks (N)":"5"}. This record does not assert independent reproduction.

### FedBCGD

Accuracy: 59.5. Result ID: 69aa9ba66dbb7075b95497c2.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

Recorded evaluation configuration: {"Heterogeneity (rho)":"0.1","Total communication floats":"1000d","Backbone":"ResNet-18","Number of blocks (N)":"5"}. This record does not assert independent reproduction.

### FedAdam

Accuracy: 49.9. Result ID: 69aa9ba66dbb7075b95497bf.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa58711e209131ce9ae27a.md>)

Recorded evaluation configuration: {"Heterogeneity (rho)":"0.1","Total communication floats":"1000d","Backbone":"ResNet-18","Number of blocks (N)":"5"}. This record does not assert independent reproduction.

### FedAvgM

Accuracy: 48.3. Result ID: 69aa9ba66dbb7075b95497be.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faa1.md>)

Recorded evaluation configuration: {"Heterogeneity (rho)":"0.1","Total communication floats":"1000d","Backbone":"ResNet-18","Number of blocks (N)":"5"}. This record does not assert independent reproduction.

### FedDC

Accuracy: 46.6. Result ID: 69aa9ba66dbb7075b95497c1.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b80.md>)

[Implementation](<https://github.com/gaoliang13/FedDC>)

Recorded evaluation configuration: {"Heterogeneity (rho)":"0.1","Total communication floats":"1000d","Backbone":"ResNet-18","Number of blocks (N)":"5"}. This record does not assert independent reproduction.

### FedAvg

Accuracy: 45.8. Result ID: 69aa9ba66dbb7075b95497bd.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

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

Recorded evaluation configuration: {"Heterogeneity (rho)":"0.1","Total communication floats":"1000d","Backbone":"ResNet-18","Number of blocks (N)":"5"}. This record does not assert independent reproduction.

### SCAFFOLD

Accuracy: 44.3. Result ID: 69aa9ba66dbb7075b95497c0.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa57fa1e209131ce9aa47a.md>)

Recorded evaluation configuration: {"Heterogeneity (rho)":"0.1","Total communication floats":"1000d","Backbone":"ResNet-18","Number of blocks (N)":"5"}. This record does not assert independent reproduction.

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