Table 6 Comparison of the complexities of our model with other models.

From: Dynamic atrous attention and dual branch context fusion for cross scale Building segmentation in high resolution remote sensing imagery

 

Params (M)

FLOPs (GFLOPS)

mIoU

DeepLabV3+

58.6

23.99

69.23

HRNet

15.86

19.96

70.71

PSPNet

53.32

28.00

68.44

Segformer

3.71

7.79

73.92

TDNet

35.86

68.79

74.44

GDGNet

19.60

221.12

74.87

SegTDformer

12.15

14.85

75.47

Back to article page