Medical Image Classification on GLV2 (test)
0.979AUCMC Dropout
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MC DropoutBackbone=ResNet18, Drop rate=0.03, Stochastic forward passes=102026.03 | 0.979 | 92.1 | |
| CUPIDBackbone=ResNet182026.03 | 0.97 | 90.9 | |
| IGRUEBackbone=ResNet182026.03 | 0.97 | 90.9 | |
| Rate-inBackbone=ResNet182026.03 | 0.97 | 90.9 | |
| BNNBackbone=ResNet182026.03 | 0.966 | 91.4 | |
| DECBackbone=ResNet182026.03 | 0.875 | 87.8 | |
| PostNetBackbone=ResNet182026.03 | 0.789 | 71.8 |