Table 9 Quantitative results of corn kernel segmentation task. (bold indicates the best)

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

Model

BN

HD

NOR

Average

mIoU

mDSC

mIoU

mDSC

mIoU

mDSC

mIoU

mDSC

U-Net

0.769

0.829

0.709

0.823

0.702

0.725

0.726

0.792

U-T

0.731

0.861

0.761

0.850

0.816

0.823

0.769

0.845

U-S

0.781

0.831

0.741

0.816

0.831

0.867

0.784

0.838

U-V

0.815

0.885

0.864

0.925

0.752

0.835

0.810

0.881

U-V + DI

0.885

0.891

0.878

0.935

0.785

0.836

0.849

0.887

U-V + MSA

0.868

0.912

0.874

0.927

0.798

0.840

0.847

0.893

U-V + MSA + DI

0.889

0.936

0.891

0.938

0.809

0.843

0.863

0.905