Anomaly Segmentation on STU (test)
96.26AUROCRelative Energy Learning (REL) + Point Raise
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Relative Energy Learning (REL) + Point RaiseAuxiliary OOD Data=true, Backbone=Mask4Former2025.11 | 96.26 | 21.69 | 10.17 | 33.98 | 83.39 | 11.64 | 28.34 | 9.71 | |
| Deep EnsembleAuxiliary OOD Data=false, Backbone=Mask4Former2025.11 | 86.74 | 58.05 | 5.17 | 16.75 | 84.49 | 10.43 | 14.16 | 8.81 | |
| Void ClassifierAuxiliary OOD Data=true, Backbone=Mask4Former2025.11 | 85.99 | 78.6 | 3.92 | 17.64 | 84.4 | 8.19 | 14.89 | 6.91 | |
| Max LogitAuxiliary OOD Data=false, Backbone=Mask4Former2025.11 | 84.53 | 81.49 | 0.95 | 26.14 | 83.06 | 2.13 | 21.71 | 1.77 | |
| RbAAuxiliary OOD Data=false, Backbone=Mask4Former2025.11 | 66.38 | 100 | 0.81 | 24.04 | 83.28 | 3.23 | 20.02 | 2.69 | |
| MC DropoutAuxiliary OOD Data=false, Backbone=Mask4Former2025.11 | 61.51 | 82.37 | 0.11 | 2.25 | 86.72 | 1.95 | 2.14 | 1.86 |