# Binary Image Classification on PneumoniaMNIST Mild Non-IID (alpha = 1.0) (test)

Source: [Binary Image Classification on PneumoniaMNIST Mild Non-IID (alpha = 1.0) (test)](<https://www.sota2.com/research/sota/binary-image-classification-on-pneumoniamnist-mild-non-iid-alpha-1-0-test>)

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

Data updated: 2026-05-26T08:38:25.320Z

Evaluation of Binary Image Classification performance on the test split of the PneumoniaMNIST Mild Non-IID dataset (alpha=1.0), reporting Accuracy, Macro-F1, and Expected Calibration Error (ECE).

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 | Binary Image Classification |
| Dataset (including any stated split) | PneumoniaMNIST Mild Non-IID (alpha = 1.0) (test) |
| Metric | Accuracy |
| 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](<https://www.sota2.com/research/sota/binary-image-classification-on-pneumoniamnist-mild-non-iid-alpha-1-0-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Macro-F1](<https://www.sota2.com/research/sota/binary-image-classification-on-pneumoniamnist-mild-non-iid-alpha-1-0-test.md?metric=Macro-F1>): Higher is better; unit: PERCENT.

- [ECE](<https://www.sota2.com/research/sota/binary-image-classification-on-pneumoniamnist-mild-non-iid-alpha-1-0-test.md?metric=ECE>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Local-Best | 89.81 | Not recorded | 6a15292cdbd7150506f7df7f |
| ChainLearn-Dropout (Ours-Dropout) | 87.63 | Not recorded | 6a15292cdbd7150506f7df7f |
| Centralized | 86.09 | Not recorded | 6a15292cdbd7150506f7df7f |
| ChainLearn (Ours) | 84.29 | Not recorded | 6a15292cdbd7150506f7df7f |
| EqualWt-Ens | 83.72 | Not recorded | 6a15292cdbd7150506f7df7f |
| FedMD | 83.21 | Not recorded | 6a15292cdbd7150506f7df7f |
| FedAvg | 76.67 | Not recorded | 6a15292cdbd7150506f7df7f |
| FedProx | 73.97 | Not recorded | 6a15292cdbd7150506f7df7f |

### Local-Best

Accuracy: 89.81. Result ID: 6a155a41fbc373592c0cbeab.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5"}. This record does not assert independent reproduction.

### ChainLearn-Dropout (Ours-Dropout)

Accuracy: 87.63. Result ID: 6a155a41fbc373592c0cbeb0.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5"}. This record does not assert independent reproduction.

### Centralized

Accuracy: 86.09. Result ID: 6a155a41fbc373592c0cbeaa.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5"}. This record does not assert independent reproduction.

### ChainLearn (Ours)

Accuracy: 84.29. Result ID: 6a155a41fbc373592c0cbeb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5"}. This record does not assert independent reproduction.

### EqualWt-Ens

Accuracy: 83.72. Result ID: 6a155a41fbc373592c0cbeaf.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5","Weighting":"Equal (Wi=1)"}. This record does not assert independent reproduction.

### FedMD

Accuracy: 83.21. Result ID: 6a155a41fbc373592c0cbeae.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa667f1e209131cea10a1d.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5","Averaging":"Temperature-scaled probabilities"}. This record does not assert independent reproduction.

### FedAvg

Accuracy: 76.67. Result ID: 6a155a41fbc373592c0cbeac.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5","Rounds":"5"}. This record does not assert independent reproduction.

### FedProx

Accuracy: 73.97. Result ID: 6a155a41fbc373592c0cbead.

[Reporting paper](<https://www.sota2.com/research/paper/6a15292cdbd7150506f7df7f.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Resolution":"224x224x3","Seeds":"5","Stabilization":"Proximal"}. This record does not assert independent reproduction.

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