Image Classification on MedMNIST OrganSMNIST (test)
76.12AccuracyWasserstein FI
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Wasserstein FIObjective Function=Wasserstein FI-based regularizer, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 76.12 | 0.9505 | 0.8325 | 19.51 | |
| ERMObjective Function=Empirical Risk Minimization, Backbone=ResNet-18, Number of repetitions=10, Input Resolution=28x282025.02 | 74.74 | 0.9615 | 1.0165 | 22.44 |