Semi-supervised Video Object Segmentation on YTVOS 2019 (val)
89.3Overall Jaccard (G)SAM 2
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| SAM 2Backbone=Hiera-L, Extra Training Data (SA-1B, SA-V)=false2024.08 | 89.3 | 87.5 | 92 | 84.8 | 92.8 | — | |
| SAM 2Backbone=Hiera-L, Extra Training Data (SA-1B, SA-V)=true2024.08 | 88.8 | 86.5 | 91 | 84.7 | 92.8 | — | |
| SAM 2Backbone=Hiera-B+, Extra Training Data (SA-1B, SA-V)=false2024.08 | 88.6 | 87.1 | 91.6 | 83.9 | 91.9 | — | |
| SAM 2Backbone=Hiera-B+, Extra Training Data (SA-1B, SA-V)=true2024.08 | 88.2 | 86.1 | 90.6 | 84 | 92.1 | — | |
| SAM 2Backbone=Hiera-S, Extra Training Data (SA-1B, SA-V)=true2024.08 | 88 | 85.9 | 90.2 | 83.9 | 91.9 | — | |
| Cutie-base+2024.08 | 87.5 | 86.3 | 90.6 | 82.7 | 90.5 | — | |
| Joint Former2024.08 | 87.4 | 86.5 | 90.9 | 82 | 90.3 | — | |
| SAM 2Backbone=Hiera-T, Extra Training Data (SA-1B, SA-V)=true2024.08 | 87.4 | 85.7 | 90.1 | 82.7 | 91.1 | — | |
| Cutie-base2024.08 | 87 | 86 | 90.5 | 82 | 89.6 | — | |
| ISVOS2024.08 | 86.3 | 85.2 | 89.7 | 81 | 89.1 | — | |
| SwinB-DeAOT-L2024.08 | 86.1 | 85.3 | 90.2 | 80.4 | 88.6 | — | |
| XMem2024.08 | 85.6 | 84.1 | 88.5 | 81 | 88.9 | — | |
| DEVA2024.08 | 85.4 | 84.9 | 89.4 | 79.6 | 87.8 | — | |
| SwinB-AOT-L2024.08 | 84.5 | 84 | 88.8 | 78.4 | 86.7 | — | |
| SimVOS-B2024.08 | 84.2 | 83.1 | — | 79.1 | — | — | |
| STCN2024.08 | 82.7 | 81.1 | 85.4 | 78.2 | 85.9 | — | |
| RDE2024.08 | 81.9 | 81.1 | 85.5 | 76.2 | 84.8 | — | |
| Cutie-baseParameters (M)=35.0, Training data ratio=0.02, Tokens ratio=12026.05 | — | — | — | — | — | 87 | |
| Cutie-base+Parameters (M)=35.0, Training data ratio=0.02, Tokens ratio=1, FPS (V100)=17.92026.05 | — | — | — | — | — | 87.5 | |
| DEVAParameters (M)=69.0, Training data ratio=0.02, Tokens ratio=12026.05 | — | — | — | — | — | 82.6 | |
| EdgeTAMParameters (M)=13.9, Training data ratio=0.92, Tokens ratio=0.14, FPS (V100)=19.22026.05 | — | — | — | — | — | 86.2 | |
| EfficientTAMParameters (M)=18.0, Training data ratio=0.92, Tokens ratio=0.25, FPS (V100)=20.12026.05 | — | — | — | — | — | 87.1 | |
| RDEParameters (M)=64.0, Training data ratio=0.02, Tokens ratio=12026.05 | — | — | — | — | — | 81.9 | |
| SAM 2.1 (T)Parameters (M)=38.9, Training data ratio=1, Tokens ratio=1, FPS (V100)=8.82026.05 | — | — | — | — | — | 87.4 | |
| SAM-I2VParameters (M)=18.9, Training data ratio=0.02, Tokens ratio=1, FPS (V100)=6.62026.05 | — | — | — | — | — | 79.8 | |
| STCNParameters (M)=54.0, Training data ratio=0.02, Tokens ratio=1, FPS (V100)=13.22026.05 | — | — | — | — | — | 82.7 | |
| TinySAM 2Parameters (M)=17.5, Training data ratio=0.03, Tokens ratio=0.07, FPS (V100)=25.62026.05 | — | — | — | — | — | 81.5 | |
| XMemParameters (M)=62.0, Training data ratio=0.02, Tokens ratio=12026.05 | — | — | — | — | — | 85.6 |