MobileViTv2 is a vision transformer that is tuned to mobile device. MobileViTv2 introduced a separable self-attention method to reduce cost than MobileViT

Usage of larger than typical convolutional kernel sizes, as also seen in 'Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs'

Large Kernel Size

ImageNet Classification with Deep Convolutional Neural Networks

MobileViTv2

Separable Self-attention for Mobile Vision Transformers

The table uniformity approach is proposed to solve the problem of dialect determination. The method is based on consistency measurement over a table Γδ
, which has been returned by parsing a CSV file with a dialect ρδ
, and the dispersion of records along with the inference of raw data types from fields.

Source	Separable Self-attention for Mobile Vision Transformers
Year
Data Source	Papers with Code archive (CC BY-SA)