Instance Segmentation on CellCountIns
55.1mAP (%)BLO-Inst
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| BLO-InstTotal Param(M)=131.63, Trainable Param(M)=38.66, Train Cost (GPU hours)=0.512026.01 | 55.1 | 83.7 | 62.5 | |
| SAM+BTotal Param(M)=111.08, Trainable Param(M)=111.08, Train Cost (GPU hours)=1.252026.01 | 50.9 | 82.3 | 60.4 | |
| RS+AnchorTotal Param(M)=117.05, Trainable Param(M)=117.05, Train Cost (GPU hours)=0.432026.01 | 49.8 | 78.7 | 55.2 | |
| SAM+MTotal Param(M)=112.18, Trainable Param(M)=112.18, Train Cost (GPU hours)=2.482026.01 | 49.7 | 74.2 | 50.9 | |
| Mask RTotal Param(M)=41.71, Trainable Param(M)=41.48, Train Cost (GPU hours)=0.382026.01 | 42 | 74.9 | 41.6 | |
| SOLOTotal Param(M)=46.23, Trainable Param(M)=46.01, Train Cost (GPU hours)=0.432026.01 | 41.6 | 63.7 | 37.4 | |
| RS+QueryTotal Param(M)=100.99, Trainable Param(M)=100.99, Train Cost (GPU hours)=1.432026.01 | 38 | 58 | 42.4 | |
| USISTotal Param(M)=698.10, Trainable Param(M)=57.02, Train Cost (GPU hours)=0.682026.01 | 34.8 | 67.6 | 33.2 |