Table 2 Comparison with other SOTA methods results.

From: Multi-branch and multi-label tree species classification using deep learning for UAV aerial photography and Sentinel remote sensing images

 

Micro

Weighted

mAP

F1

Precision

Recall

F1

Precision

Recall

TResNet 45

69.35

75.62

65.20

69.34

79.05

65.20

72.75

ML-Decoder + ViT 46

60.21

59.22

65.93

63.36

64.57

65.93

59.57

ML-Decoder + Swin 46

61.15

60.38

66.55

61.06

65.80

66.55

60.55

ASL + SAL 44,48

68.33

73.66

64.84

69.25

76.89

64.84

69.53

MMTSC

72.05

79.44

67.42

71.73

82.62

67.42

76.60

Back to article page