Skip to main content

Table 5 Test metric results for each semantic segmentation method for each dataset without patching. An explanation of the metrics can be found in "Experiment configurations" section

From: CEU-Net: ensemble semantic segmentation of hyperspectral images using clustering

Methods

OA

AA

Kappa

OA

AA

Kappa

 

IP (k = 2)

Salinas (k = 3)

HybridSN

86.99 ± 0.1

86.5 ± 0.2

85.69 ± 0.1

96.74 ± 0.1

97.62 ± 0.1

96.37 ± 0.1

AeroRIT

74.44 ± 0.2

65.5 ± 0.3

70.97 ± 0.2

95.06 ± 0.1

97.7 ± 0.1

94.49 ± 0.1

U-Net

87.25 ± 0.1

87.8 ± 0.2

85.64 ± 0.1

96.78 ± 0.1

98.24 ± 0.1

96.37 ± 0.1

CEU-Net

90.01 ± 0.1

90.52 ± 0.2

88.67 ± 0.1

96.44 ± 0.1

98.36 ± 0.1

96.34 ± 0.1

 

KSC (k = 2)

Botswana (k = 3)

HybridSN

94.85 ± 0.1

91.9 ± 0.1

94.27 ± 0.1

96.29 ± 0.2

96.5 ± 0.2

96.92 ± 0.2

AeroRIT

93.94 ± 0.1

91.15 ± 0.2

93.23 ± 0.1

89.7 ± 0.3

89.95 ± 0.3

88.77 ± 0.2

U-Net

95.00 ± 0.1

92.73 ± 0.1

94.93 ± 0.1

96.77 ± 0.2

96.45 ± 0.2

96.94 ± 0.2

CEU-Net

95.25 ± 0.1

93.05 ± 0.1

94.98 ± 0.1

96.43 ± 0.2

97.1 ± 0.2

96.13 ± 0.2

 

PU (k = 2)

Houston (k = 2)

HybridSN

95.99 ± 0.1

94.59 ± 0.1

94.71 ± 0.1

98.3 ± 0.1

98.2 ± 0.1

98.17 ± 0.1

AeroRIT

93.89 ± 0.1

91.56 ± 0.2

91.9 ± 0.2

93.98 ± 0.1

93.99 ± 0.2

93.49 ± 0.1

U-Net

96.02 ± 0.1

94.95 ± 0.1

94.86 ± 0.1

98.38 ± 0.1

98.21 ± 0.1

98.25 ± 0.1

CEU-Net

96.18 ± 0.1

95.1 ± 0.1

95.00 ± 0.1

98.49 ± 0.1

98.38 ± 0.1

98.36 ± 0.1

  1. Highest performing values are highlighted in bold