Lesion Segmentation On University Of Waterloo

Dice score

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Dice score	Paper Title	Repository
DeepLabV3+	0.883 ±0.108	Skin Lesion Segmentation Using Atrous Convolution via DeepLab v3	-
U-Net	0.836 ±0.132	U-Net: Convolutional Networks for Biomedical Image Segmentation
DTP-Net	0.884 ±0.100	DTP-Net: A convolutional neural network model to predict threshold for localizing the lesions on dermatological macro-images
FCN-8s	0.870 ±0.063	Fully Connected Deep Structured Networks	-
SegNet	0.854 ±0.088	SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

0 of 5 row(s) selected.