Video Object Discovery on YTVIS-HQ real-world (test)
42.4ARISmoothSA
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SmoothSA#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 42.4 | 63 | 38.9 | 38.3 | |
| SmoothSA + ICC#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 42.1 | 60.2 | 39.6 | 39.2 | |
| RandSF.Q + ICC#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 40.6 | 60.1 | 39.2 | 38.9 | |
| SmoothSA + ECC#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 40.2 | 59.8 | 38 | 37.2 | |
| RandSF.Q#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 40.1 | 58 | 37.6 | 37.2 | |
| RandSF.Q + ECC#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 40 | 57.2 | 37 | 36.2 | |
| SlotContrast#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 37.2 | 49.4 | 33 | 32.8 | |
| VideoSAUR#slot=7, conditional=true, Input resolution=224x224, Encoder=DINO2 ViT-S/14, Seeds=42, 43, 442026.05 | 33.8 | 49.2 | 29.9 | 29.7 |