Table 7 Compared with different attention modules.

From: Spatially adaptive interaction network for semantic segmentation of high-resolution remote sensing images

Method

Dataset

DeepGlobe

Vaihingen

Potsdam

CAM80

71.9

78.6

79.0

SAM81

71.5

78.3

78.9

CBAM82

72.3

79.1

79.7

Ours

77.8

82.5

88.3

  1. Significant values are in bold.
Back to article page