Instance Segmentation on RWCellIns
78.5mAPBLO-Inst
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BLO-InstTotal Param(M)=131.63, Trainable Param(M)=38.66, Train Cost (GPU hours)=0.512026.01 | 78.5 | 94.6 | 89.8 | |
| SAM+BTotal Param(M)=111.08, Trainable Param(M)=111.08, Train Cost (GPU hours)=1.252026.01 | 76.1 | 91.6 | 88.2 | |
| RS+AnchorTotal Param(M)=117.05, Trainable Param(M)=117.05, Train Cost (GPU hours)=0.432026.01 | 76.1 | 92.5 | 88.1 | |
| SAM+MTotal Param(M)=112.18, Trainable Param(M)=112.18, Train Cost (GPU hours)=2.482026.01 | 75 | 91.8 | 84.7 | |
| USISTotal Param(M)=698.10, Trainable Param(M)=57.02, Train Cost (GPU hours)=0.682026.01 | 74.3 | 90.8 | 85.2 | |
| RS+QueryTotal Param(M)=100.99, Trainable Param(M)=100.99, Train Cost (GPU hours)=1.432026.01 | 71.5 | 90.4 | 83.4 | |
| SOLOTotal Param(M)=46.23, Trainable Param(M)=46.01, Train Cost (GPU hours)=0.432026.01 | 64.7 | 89.5 | 74.6 | |
| Mask RTotal Param(M)=41.71, Trainable Param(M)=41.48, Train Cost (GPU hours)=0.382026.01 | 63.2 | 90.5 | 76.7 |