Conformal Prediction on ImageNet (val)
76.15Top-1 AccuracyLabel Distance
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Label DistanceConformal domain=Probability space, Distance metric=Cosine distance, Model=ResNet-502026.05 | 76.15 | 92.87 | 8.456 | |
| Margin DistanceConformal domain=Logit space, Distance metric=Cosine distance, Model=ResNet-502026.05 | 76.15 | 92.87 | 8.122 | |
| Mean DistanceConformal domain=Probability space, Distance metric=Cosine distance, Model=ResNet-502026.05 | 76.15 | 92.87 | 8.527 | |
| APS (U=0.001)Conformal domain=Probability space, Distance metric=N/A, Model=ResNet-502026.05 | 76.15 | 92.87 | 15.49 | |
| RAPS (λ = 0.2, k = 1, U=0.001)Conformal domain=Probability space, Distance metric=N/A, Model=ResNet-502026.05 | 76.15 | 92.87 | 9.921 | |
| SAPS (λ = 0.2, U=0.001)Conformal domain=Probability space, Distance metric=N/A, Model=ResNet-502026.05 | 76.15 | 92.87 | 9.603 |