Image Classification on MedMNIST BreastMNIST (test)
86.35AccuracyWasserstein FI
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Wasserstein FIObjective Function=Wasserstein FI-based regularizer, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 86.35 | 87.78 | 0.3661 | 18.44 | |
| ERMObjective Function=Empirical Risk Minimization, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 83.91 | 86.38 | 0.5832 | 25.25 |