Cardiac Multi-structures Segmentation on ACDC (val)
91.94DSCAttention-Mamba
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Attention-MambaParam (M)=14.05, FLOPs (G)=5.04, Training Size=192 × 1922024.02 | 91.94 | 85.61 | 4.61 | |
| DualAttenUNetParam (M)=19.57, FLOPs (G)=16.23, Training Size=192 × 1922024.02 | 91.81 | 85.24 | 4.13 | |
| MulitTransParam (M)=39.38, FLOPs (G)=13.43, Training Size=192 × 1922024.02 | 91.81 | 85.33 | 5.37 | |
| VM UNet V2Param (M)=22.77, FLOPs (G)=2.48, Training Size=192 × 1922024.02 | 91.71 | 85.14 | 4.76 | |
| Swin UMambaParam (M)=59.89, FLOPs (G)=24.65, Training Size=192 × 1922024.02 | 91.61 | 84.98 | 6.39 | |
| AttenUNetParam (M)=34.88, FLOPs (G)=37.45, Training Size=192 × 1922024.02 | 91.56 | 84.93 | 5.53 | |
| UNetPlusPlusParam (M)=9.16, FLOPs (G)=19.62, Training Size=192 × 1922024.02 | 91.48 | 84.83 | 5.85 | |
| HiFormerParam (M)=37.46, FLOPs (G)=17.51, Training Size=224 × 2242024.02 | 91.23 | 84.3 | 4.54 | |
| H2FormerParam (M)=33.68, FLOPs (G)=18.12, Training Size=192 × 1922024.02 | 90.99 | 84.03 | 4.69 | |
| UnetParam (M)=31.04, FLOPs (G)=30.75, Training Size=192 × 1922024.02 | 90.95 | 83.86 | 5.93 | |
| VM UNetParam (M)=27.43, FLOPs (G)=2.32, Training Size=192 × 1922024.02 | 90.32 | 82.88 | 5.37 | |
| SwinUNetParam (M)=27.17, FLOPs (G)=5.95, Training Size=224 × 2242024.02 | 89.74 | 81.93 | 5.66 | |
| Mamba UNetParam (M)=19.12, FLOPs (G)=2.60, Training Size=192 × 1922024.02 | 89.63 | 81.79 | 6.5 | |
| MISSFormerParam (M)=42.46, FLOPs (G)=7.28, Training Size=224 × 2242024.02 | 88.51 | 79.99 | 8.16 |