Video Object Segmentation on DAVIS 17
90J ScoreOurs
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Ours2025.03 | 90 | — | 89 | |
| XMemSegmentation Data=Image+VOS+DAVIS (0.25M), Type=Video, Refer-Type=Mask, Zero-Shot=false, Single Image=false2023.04 | 85.1 | 86.1 | 89.8 | |
| MIVOSSegmentation Data=BL30K+VOS+DAVIS (4.88M), Type=Mask/Scribble, Refer-Type=Mask, Zero-Shot=false, Single Image=false2023.04 | 81.7 | 84.5 | 87.4 | |
| SWEMSegmentation Data=Image+VOS+DAVIS (0.25M), Type=Mask, Refer-Type=Mask, Zero-Shot=false, Single Image=false2023.04 | 81.2 | 84.3 | 87.4 | |
| OCLR-TTA2025.03 | 76 | — | 75.3 | |
| ABR2025.03 | 74.6 | — | 75.2 | |
| UNINEXT-LSegmentation Data=Image+Video (3M), Type=Generalist, Refer-Type=Mask, Zero-Shot=false, Single Image=false2023.04 | 73.2 | 77.2 | 81.2 | |
| SegGPT-LSegmentation Data=COCO+ADE+VOC+... (0.25M), Type=Generalist, Refer-Type=Mask, Zero-Shot=false, Single Image=true2023.04 | 72.5 | 75.6 | 78.6 | |
| UNINEXT-TSegmentation Data=Image+Video (3M), Type=Generalist, Refer-Type=Mask, Zero-Shot=false, Single Image=false2023.04 | 71.3 | 74.5 | 77.6 | |
| Pi3MOS-SLAM2025.12 | 70.6 | — | 81.3 | |
| OCLR-flow2025.03 | 69.9 | — | 70 | |
| AGAMESegmentation Data=(Synth)VOS+DAVIS (0.11M), Type=Mask, Refer-Type=Mask, Zero-Shot=false, Single Image=false2023.04 | 67.2 | 70 | 72.7 | |
| AGSSSegmentation Data=VOS+DAVIS (0.1M), Type=Mask, Refer-Type=Mask, Zero-Shot=false, Single Image=false2023.04 | 64.9 | 67.4 | 69.9 | |
| UNINEXT-L (Text)Segmentation Data=Image+Video (3M), Type=Generalist, Refer-Type=Text, Zero-Shot=false, Single Image=false2023.04 | 62.3 | 66.7 | 71.1 | |
| SEEM-BSegmentation Data=COCO+LVIS (0.12M), Type=Generalist, Refer-Type=Mask/Single Point, Zero-Shot=true, Single Image=true2023.04 | 59.5 | 62.8 | 66.2 | |
| SEEM-LSegmentation Data=COCO+LVIS (0.12M), Type=Generalist, Refer-Type=Mask/Single Point, Zero-Shot=true, Single Image=true2023.04 | 58.3 | 62.2 | 66 | |
| ReferFormer-BSegmentation Data=RefCOCO(+/g)+VOS+DAVIS (0.13M), Type=Text, Refer-Type=Text, Zero-Shot=false, Single Image=false2023.04 | 58.1 | 61.1 | 64.1 | |
| SEEM-TSegmentation Data=COCO+LVIS (0.12M), Type=Generalist, Refer-Type=Mask/Single Point, Zero-Shot=true, Single Image=true2023.04 | 57.6 | 60.4 | 63.3 | |
| PerSAM-LSegmentation Data=SAM+DAVIS (11M), Type=Generalist, Refer-Type=Mask, Zero-Shot=true, Single Image=true2023.04 | 56.6 | 60.3 | 63.9 | |
| Easi3Rbase_model=MonST3R2025.12 | 56.5 | — | 68.6 | |
| Easi3Rbase_model=DUSt3R2025.12 | 49 | — | 56.4 | |
| DAS3R2025.12 | 43.5 | — | 42.1 | |
| MonST3R2025.12 | 38.6 | — | 38.2 | |
| DUSt3R2025.12 | 35.2 | — | 35.3 | |
| Painter-LSegmentation Data=COCO+ADE+NYUv2 (0.16M), Type=Generalist, Refer-Type=Mask, Zero-Shot=false, Single Image=true2023.04 | 28.5 | 34.6 | 40.8 | |
| SAM 2.1Model Scale=L2024.10 | — | 90.1 | — | |
| SAM2.1LongModel Scale=L2024.10 | — | 90.2 | — |