Image Classification on PneumoniaMNIST MedMNIST (test)
0.9556AUCERM
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ERMObjective Function=Empirical Risk Minimization, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 0.9556 | 85.88 | 0.6262 | 13.41 | |
| Wasserstein FIObjective Function=Wasserstein FI-based regularizer, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 0.9343 | 85.72 | 0.4238 | 12.81 | |
| BRAL-TTarget Model=ResNet182026.04 | 0.738 | — | — | 88.3 | |
| LossPredictionTarget Model=ResNet182026.04 | 0.732 | — | — | 87 | |
| RandomSampleTarget Model=ResNet182026.04 | 0.706 | — | — | 65.2 | |
| WAALTarget Model=ResNet182026.04 | 0.64 | — | — | 87 |