Table 8 Segmentation results with different backbone networks.

From: Multilevel support-assisted prototype optimization network for few-shot medical segmentation of lung lesions

Multilevel Prototypes

Weight Factor

VGG-16

ResNet-101

\(\:{p}_{conv4}\)

[1]

0.8535

0.7626

\(\:{p}_{conv4}\), \(\:{p}_{conv5}\)

[0.8, 0.2]

0.8647

0.8027

\(\:{p}_{conv3}\), \(\:{p}_{conv4}\), \(\:{p}_{conv5}\)

[0.2, 0.6, 0.2]

0.8671

0.8035

Back to article page