CSAT	Convolutional neural network with Spatial Attention by Transformer
CFC	Channel-wise Fully Connected
GRN	Global Response Normalization
KD	Knowledge Distillation
MAC	Multiply ACcumulate
MAE	Masked Auto Encoder
RCKD	Response based Cross task Knowledge Distillation
PEG	Position Encoding Generator
RKD	Response-based Knowledge Distillation
SAT	Spatial Attntion by Transformer
SGD	Stochastic Gradient Descent
SOTA	State Of The Art
SPT	Supervised PreTraining
SSL	Self Supervised Learning
USI	Unified Scheme for ImageNet
ViT	Vision Transformer
WSI	Whole Slide Imaging