Table 10 Performance of each component (only decoder) on the polyp dataset.
From: VMKLA-UNet: vision Mamba with KAN linear attention U-Net
Model | SS2D | Linear | KAN linear | CSA | Kvair | ClinicDB | ColonDB | ETIS | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
mIou | Dsc | mIou | Dsc | mIou | Dsc | mIou | Dsc | |||||
Baseline | √ | 80.32 | 89.09 | 81.95 | 90.08 | 55.28 | 71.20 | 66.41 | 79.81 | |||
Only-CSA | √ | 79.44 | 88.95 | 80.55 | 88.76 | 59.13 | 73.76 | 55.36 | 66.52 | |||
MLLA | √ | 82.12 | 90.12 | 83.36 | 90.14 | 58.74 | 70.34 | 58.21 | 68.33 | |||
MKLA | √ | 83.54 | 90.11 | 83.58 | 92.31 | 59.44 | 75.14 | 68.71 | 78.37 | |||
MLCSA | √ | √ | 84.96 | 90.88 | 88.78 | 94.15 | 64.14 | 76.55 | 68.14 | 79.21 | ||
Ours | √ | √ | 86.43 | 92.72 | 90.64 | 95.09 | 64.90 | 78.72 | 73.53 | 84.74 | ||
