Multi-class Classification on Caltech Birds (test)
8.3Average Prediction Set SizePCS Original
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PCS OriginalBackbone=Res-net 18, Target coverage=90%, Number of bootstraps (B)=1002025.05 | 8.3 | 100 | |
| PCS NoiseBackbone=Res-net 18, Target coverage=90%, Number of bootstraps (B)=10002025.05 | 9.4 | 3 | |
| PCS DropoutBackbone=Res-net 18, Target coverage=90%, Number of bootstraps (B)=10002025.05 | 9.8 | 3 | |
| RAPSBackbone=Res-net 18, Target coverage=90%2025.05 | 12.8 | 2 | |
| APSBackbone=Res-net 18, Target coverage=90%2025.05 | 16.6 | 2 | |
| TopKBackbone=Res-net 18, Target coverage=90%2025.05 | 17.6 | 2 |