Image Classification on BloodMNIST MedMNIST (test)
95.01AccuracyWasserstein FI
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Wasserstein FIObjective Function=Wasserstein FI-based regularizer, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 95.01 | 99.47 | 0.177 | 5.52 | |
| ERMObjective Function=Empirical Risk Minimization, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 94.64 | 99.58 | 0.1836 | 5.85 |