Video Instance Segmentation on OVIS (diagnostic)
73.6APMinVIS
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| MinVISBackbone=Swin-L, Variation=TC-Oracle2026.06 | 73.6 | 96.8 | 86 | 25.2 | 76.3 | 25.7 | 3.1 | |
| VISAGEBackbone=ResNet-50, Variation=TC-Oracle2026.06 | 72.6 | 96.4 | 83.6 | 25.4 | 76.6 | 16.1 | 2.5 | |
| VISAGEBackbone=ResNet-50, Variation=T-Oracle2026.06 | 72.2 | 95.8 | 83 | 25.1 | 76 | 15.7 | 2.2 | |
| MinVISBackbone=Swin-L, Variation=T-Oracle2026.06 | 71.8 | 95.8 | 81.8 | 24.7 | 75 | 23.9 | 2.6 | |
| DVIS++Backbone=Swin-L, Variation=TC-Oracle2026.06 | 69.2 | 92.8 | 79.5 | 24.4 | 72.3 | 8.5 | 1.1 | |
| CAVISBackbone=Swin-L, Variation=TC-Oracle2026.06 | 69.1 | 93.4 | 78.3 | 24.5 | 72.2 | 9.9 | 1.5 | |
| CAVISBackbone=Swin-L, Variation=T-Oracle2026.06 | 68.7 | 92.5 | 77.7 | 24.3 | 71.9 | 9.5 | 1.3 | |
| GenVISBackbone=Swin-L, Variation=TC-Oracle2026.06 | 68.6 | 92.8 | 77.4 | 24.7 | 71 | 14 | 1.8 | |
| DVIS++Backbone=Swin-L, Variation=T-Oracle2026.06 | 68.4 | 92 | 78.4 | 24.2 | 71.7 | 7.7 | 0.9 | |
| GenVISBackbone=Swin-L, Variation=T-Oracle2026.06 | 68.2 | 92.2 | 77.4 | 24.6 | 70.9 | 13.6 | 1.7 | |
| DVISBackbone=Swin-L, Variation=TC-Oracle2026.06 | 68.2 | 92.5 | 77.8 | 24.3 | 71.7 | 11.3 | 2.1 | |
| CAVISBackbone=ResNet-50, Variation=TC-Oracle2026.06 | 67.8 | 96 | 76.3 | 24.3 | 70.2 | 13.2 | 2 | |
| CTVISBackbone=ResNet-50, Variation=TC-Oracle2026.06 | 67.7 | 96.3 | 74 | 24.3 | 69.9 | 20.4 | 4.3 | |
| MinVISBackbone=ResNet-50, Variation=TC-Oracle2026.06 | 67.6 | 95.9 | 74.7 | 24.3 | 70.4 | 24 | 4.3 | |
| CAVISBackbone=ResNet-50, Variation=T-Oracle2026.06 | 67.4 | 95.1 | 75.7 | 24.1 | 69.9 | 12.8 | 1.8 | |
| CTVISBackbone=Swin-L, Variation=TC-Oracle2026.06 | 67.3 | 91.5 | 75.4 | 24.6 | 71.8 | 17.1 | 2.8 | |
| CTVISBackbone=ResNet-50, Variation=T-Oracle2026.06 | 66.7 | 94.3 | 73 | 24 | 69.1 | 19.4 | 4 | |
| MinVISBackbone=ResNet-50, Variation=T-Oracle2026.06 | 66.4 | 93.6 | 74.1 | 23.8 | 69.3 | 22.8 | 3.8 | |
| DVISBackbone=Swin-L, Variation=T-Oracle2026.06 | 66.3 | 90 | 75.2 | 23.8 | 70 | 9.4 | 1.6 | |
| DVIS++Backbone=ResNet-50, Variation=T-Oracle2026.06 | 64.8 | 93.7 | 71.5 | 23.4 | 67.4 | 12.4 | 1.3 | |
| DVIS++Backbone=ResNet-50, Variation=TC-Oracle2026.06 | 64 | 92.4 | 70.3 | 23.6 | 66.9 | 11.6 | 1.5 | |
| CTVISBackbone=Swin-L, Variation=T-Oracle2026.06 | 63.8 | 86.2 | 70.8 | 24.1 | 70.5 | 13.6 | 2.3 | |
| DVISBackbone=ResNet-50, Variation=TC-Oracle2026.06 | 63 | 92.1 | 68.6 | 23.5 | 66.3 | 14.4 | 2.5 | |
| DVISBackbone=ResNet-50, Variation=T-Oracle2026.06 | 62.7 | 91.7 | 68.3 | 23 | 65.7 | 14.1 | 2 | |
| GenVISBackbone=ResNet-50, Variation=TC-Oracle2026.06 | 62.3 | 92 | 66.4 | 23.1 | 66.4 | 12.6 | 2 | |
| GenVISBackbone=ResNet-50, Variation=T-Oracle2026.06 | 61.6 | 90.9 | 65.6 | 23 | 65.9 | 11.9 | 1.8 | |
| DVIS++Backbone=Swin-L, Variation=Default2026.06 | 60.7 | 85.6 | 66.7 | 23.3 | 63.1 | — | — | |
| CAVISBackbone=Swin-L, Variation=Default2026.06 | 59.2 | 82.9 | 65.6 | 23 | 62.8 | — | — | |
| DVISBackbone=Swin-L, Variation=Default2026.06 | 56.9 | 80.2 | 62.7 | 22.2 | 61.4 | — | — | |
| VISAGEBackbone=ResNet-50, Variation=Default2026.06 | 56.5 | 77.5 | 62.7 | 23 | 58 | — | — | |
| GenVISBackbone=Swin-L, Variation=Default2026.06 | 54.6 | 76.3 | 59 | 22.9 | 56.7 | — | — | |
| CAVISBackbone=ResNet-50, Variation=Default2026.06 | 54.6 | 80.4 | 59.5 | 22.3 | 58.1 | — | — | |
| DVIS++Backbone=ResNet-50, Variation=Default2026.06 | 52.4 | 77.9 | 55.3 | 22.1 | 55.4 | — | — | |
| CTVISBackbone=Swin-L, Variation=Default2026.06 | 50.2 | 70.4 | 53.9 | 21.8 | 54.9 | — | — | |
| GenVISBackbone=ResNet-50, Variation=Default2026.06 | 49.7 | 72.5 | 50.6 | 21.2 | 51.6 | — | — | |
| DVISBackbone=ResNet-50, Variation=Default2026.06 | 48.6 | 72.5 | 51.3 | 21 | 53.7 | — | — | |
| MinVISBackbone=Swin-L, Variation=Default2026.06 | 47.9 | 67.6 | 52.4 | 22.1 | 51.2 | — | — | |
| CTVISBackbone=ResNet-50, Variation=Default2026.06 | 47.3 | 69.6 | 50.1 | 20 | 52.4 | — | — | |
| MinVISBackbone=ResNet-50, Variation=Default2026.06 | 43.6 | 63.7 | 46.3 | 20 | 46.4 | — | — |