DAT++: Spatially Dynamic Vision Transformer with Deformable Attention.

Zhuofan Xia Xuran Pan Shiji Song Li Erran Li Gao Huang

Published in: CoRR (2023)

Keyphrases

computer vision
image processing
vision system
visual attention
databases
fuzzy logic
dynamic environments
saliency map
dynamically changing
data sets
web pages
medical images
particle swarm optimization
visual field
deformable shapes