Skin Cancer Segmentation and Classification Using Vision Transformer for Automatic Analysis in Dermatoscopy-Based Noninvasive Digital System

Table 7

Accuracy difference.

Model	Training accuracy	Test accuracy	Accuracy difference
ViT-Google	0.99375	0.9615	0.03225
ViT-MAE	0.96975	0.9215	0.04825
ViT-ResNet50	0.87175	0.8090	0.06275
ViT-VAN	0.95825	0.9240	0.03425
ViT-BEiT	0.92500	0.8625	0.06250
ViT-DiT	0.86175	0.8190	0.04275