Table 5 Presents a comparison of classification data for classical models on the GC-10 dataset.

From: High precision classification of hot rolled strip steel surface defects using dual path features and entropy attention fusion

Model

Accuracy(%)

Precision(%)

F1-score(%)

Recall(%)

ResNet18

75.23

74.83

74.56

73.38

Yolov7

80.11

78.87

80.48

81.22

Yolov10

84.21

80.47

82.68

83.17

Ourwork

82.89

86.57

81.73

82.77

Back to article page