# Image Classification on PneumoniaMNIST alpha = 0.1 (Severe Non-IID) (test) Source: [Image Classification on PneumoniaMNIST alpha = 0.1 (Severe Non-IID) (test)]() Collection index: [llms.txt]() Data updated: 2026-05-26T08:38:25.280Z Evaluation of Image Classification performance on the test split of the PneumoniaMNIST dataset configured with alpha=0.1 (Severe Non-IID distribution), 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 | Image Classification | | Dataset (including any stated split) | PneumoniaMNIST alpha = 0.1 (Severe Non-IID) (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](): Higher is better; unit: PERCENT. - [Macro-F1](): Higher is better; unit: PERCENT. - [ECE](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Local-Best | 89.1 | Not recorded | 6a15292cdbd7150506f7df7f | | Ours-Dropout | 87.5 | Not recorded | 6a15292cdbd7150506f7df7f | | Centralized | 86.54 | Not recorded | 6a15292cdbd7150506f7df7f | | Ours | 78.53 | Not recorded | 6a15292cdbd7150506f7df7f | | FedMD | 77.76 | Not recorded | 6a15292cdbd7150506f7df7f | | FedAvg | 75.9 | Not recorded | 6a15292cdbd7150506f7df7f | | EqualWt-Ens | 72.44 | Not recorded | 6a15292cdbd7150506f7df7f | | FedProx | 71.35 | Not recorded | 6a15292cdbd7150506f7df7f | ### Local-Best Accuracy: 89.1. Result ID: 6a155a41fbc373592c0cbea3. [Reporting paper]() Recorded evaluation configuration: {"training\_mode":"independent hospital training"}. This record does not assert independent reproduction. ### Ours-Dropout Accuracy: 87.5. Result ID: 6a155a41fbc373592c0cbea8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ablation":"dropout"}. This record does not assert independent reproduction. ### Centralized Accuracy: 86.54. Result ID: 6a155a41fbc373592c0cbea2. [Reporting paper]() Recorded evaluation configuration: {"training\_mode":"pooled data"}. This record does not assert independent reproduction. ### Ours Accuracy: 78.53. Result ID: 6a155a41fbc373592c0cbea9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"protocol":"ChainLearn"}. This record does not assert independent reproduction. ### FedMD Accuracy: 77.76. Result ID: 6a155a41fbc373592c0cbea6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"aggregation":"temperature-scaled probabilities"}. This record does not assert independent reproduction. ### FedAvg Accuracy: 75.9. Result ID: 6a155a41fbc373592c0cbea4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"rounds":"5","backbone":"ResNet-50"}. This record does not assert independent reproduction. ### EqualWt-Ens Accuracy: 72.44. Result ID: 6a155a41fbc373592c0cbea7. [Reporting paper]() Recorded evaluation configuration: {"weighting":"equal (Wi=1)"}. This record does not assert independent reproduction. ### FedProx Accuracy: 71.35. Result ID: 6a155a41fbc373592c0cbea5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"stabilization":"proximal"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.