OOD Detection on Medical (OOD) WMT15 En-Fr (ID) (test)
82.39AUROCKNN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| KNNBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.02 | 82.39 | 65.91 | |
| AP-OODOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 81.44 | 80.53 | |
| AP-OODOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 81.28 | 79.79 | |
| Deep SADOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 80.55 | 81.62 | |
| AP-OODBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.02 | 80.16 | 61.55 | |
| AP-OODBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.02 | 78.74 | 62.26 | |
| MahalanobisBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.02 | 78.63 | 67.14 | |
| Deep SVDDBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.02 | 78.46 | 68.94 | |
| MahalanobisBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.02 | 78.22 | 73.03 | |
| KNNBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Input, Unsupervised=true2026.02 | 77.86 | 68.95 | |
| Deep SADOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 77.14 | 72.54 | |
| Deep SVDDBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.02 | 76.47 | 72.8 | |
| Binary logitsOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 73.81 | 80.14 | |
| PerplexityBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.02 | 73.05 | 70.47 | |
| Binary logitsOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 72.91 | 83.66 | |
| Relative MahalanobisOOD level=Input, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 67.2 | 79.45 | |
| Relative MahalanobisOOD level=Output, Learning paradigm=Supervised, Backbone=Transformer (base)2026.02 | 66.17 | 82.28 | |
| EntropyBackbone=Transformer (base), Training Data=WMT15 En-Fr, Evaluation Side=Output, Unsupervised=true2026.02 | 50.51 | 90.21 |