Skip to main content

Table 8 The results of comparison with classical models

From: Automated fundus ultrasound image classification based on siamese convolutional neural networks with multi-attention

Model

Accuracy

Precision

Recall

F1

SVK_MA

0.940

0.941

0.940

0.939

VIT [29]

0.917

0.923

0.909

0.916

Swin-T [30]

0.880

0.923

0.845

0.882

VGG16

0.903

0.906

0.903

0.903

Alexnet [31]

0.841

0.831

0.851

0.839

Resnet18 [32]

0.876

0.876

0.876

0.876