Out-of-Distribution Detection on FashionMNIST (ID) vs KMNIST (OOD) (test)
92.5AUROCLIN-RIEM-LA
Evaluation results
| Method | Links | |
|---|---|---|
| LIN-RIEM-LAPrior Precision=Not Optimized, Exponential Maps Source=Subset of Training Set2023.06 | 92.5 | |
| LIN-LAPrior Precision=Not Optimized2023.06 | 92.4 | |
| LIN-RIEM-LAPrior Precision=Not Optimized, Exponential Maps Source=Full Training Set2023.06 | 92.1 | |
| RIEM-LAPrior Precision=Optimized, Exponential Maps Source=Full Training Set2023.06 | 91 | |
| RIEM-LAPrior Precision=Optimized, Exponential Maps Source=Subset of Training Set2023.06 | 90.7 | |
| RIEM-LAPrior Precision=Not Optimized, Exponential Maps Source=Subset of Training Set2023.06 | 89.8 | |
| RIEM-LAPrior Precision=Not Optimized, Exponential Maps Source=Full Training Set2023.06 | 88.6 | |
| LIN-RIEM-LAPrior Precision=Optimized, Exponential Maps Source=Subset of Training Set2023.06 | 84.9 | |
| LIN-LAPrior Precision=Optimized2023.06 | 84.6 | |
| Vanilla LAPrior Precision=Optimized2023.06 | 82.7 | |
| LIN-RIEM-LAPrior Precision=Optimized, Exponential Maps Source=Full Training Set2023.06 | 80 | |
| MAPPrior Precision=Not Optimized2023.06 | 71.8 | |
| MAPPrior Precision=Optimized2023.06 | 71.8 | |
| Vanilla LAPrior Precision=Not Optimized2023.06 | 49.5 |