Table 10 Performance comparison of model size (Params) between VMUnet-MSADI and other leading methods on the GaoZhe dataset.

From: Visual Mamba UNet fusion multi-scale attention and detail infusion for unsound corn kernels segmentation

Model

year

mIoU

mDSC

Params

Unet2

2015

0.554

0.754

24.55 M

UnetV247

2018

0.537

0.732

25.12 M

Unet++4

2019

0.575

0.751

26.04 M

Att-Unet48

2020

0.835

0.832

29.32 M

TransUNet54

2018

0.604

0.764

25.23 M

TransFuse55

2021

0.611

0.801

106.87 M

Swin-Unet56

2021

0.814

0.806

114.65 M

DoubleU-Net37

2021

0.822

0.811

148.96 M

VMUNet52

2024

0.845

0.865

86.54 M

VMUNetV253

2024

0.846

0.905

96.81 M

VMUnet-MSADI

 

0.853

0.919

103.23 M

Back to article page