Skip to main content

Table 3 Comparison of the accuracy of different kinds of base network

From: DM_CorrMatch: a semi-supervised semantic segmentation framework for rapeseed flower coverage estimation using UAV imagery

Base Network

Precision

Recall

IoU

F1 Score

Accuracy

F(G)/P(M)

UNet

0.918

0.912

0.865

0.915

0.928

83.46/66.37

SegNet

0.910

0.900

0.858

0.905

0.920

79.67/74.21

Deeplabv3+

0.932

0.929

0.856

0.930

0.938

80.35/71.72

Mamba-Deeplabv3+

0.942

0.940

0.886

0.941

0.949

85.54/76.78

HRNet

0.922

0.913

0.848

0.917

0.926

88.23/71.41

SegFormer

0.925

0.912

0.872

0.918

0.932

90.12/99.32

  1. Bold values emphasize the base network, the Mamba module, and our proposed DM_CorrMatch method, respectively, and mark the best accuracy attained under each experimental condition
Back to article page

Plant Methods

ISSN: 1746-4811