Table 3 Evaluation results of different feature fusion techniques on the proposed DBD400 testing set

From: STEF: a Swin Transformer-Based Enhanced Feature Pyramid Fusion Model for Dongba character detection

Different feature fusion

Precision

Recall

F-measure

Params

FCN [47]

70.50

65.38

67.84

3.32 M

FPNF [19]

79.01

81.09

80.04

19.51 M

FPEM+Add [20]

80.29

84.54

82.36

1.29 M

FPEM+Concat [20]

86.71

85.45

86.08

1.29 M

FPEM+FUSION

88.88

88.65

88.76

1.79 M

  1. ‘Add’ for summation fusion and ‘Concat’ for concatenation fusion. The best performers are highlighted in bold
Back to article page