Table 4 Comparison of the OBI classification accuracy of different models on OBIR-100 (%)

From: OBI-CMF: Self-supervised learning with contrastive masked frequency modeling for oracle bone inscription recognition

Method

Supervised

Top-1

Top-5

GoogLeNet49

T

94.00

98.50

DenseNet19

T

94.40

98.51

ResNet14

T

94.31

98.50

VGG13

T

89.03

97.19

ViT28

T

93.30

98.45

SimSiam32

F

91.92

98.05

MoCov333

F

92.10

97.89

MAE26

F

94.51

98.85

MFM30

F

94.86

98.81

Ours

F

95.08

98.86

  1. Values in bold indicate optimal results.
  2. T/F represents True/False.
Back to article page