Do We Really Need Explicit Position Encodings for Vision Transformers?

Xiangxiang Chu Bo Zhang Zhi Tian Xiaolin Wei Huaxia Xia

Published in: CoRR (2021)

Keyphrases

computer vision
real time
vision system
image processing
computational vision
image segmentation
visual perception
active vision
real world
information retrieval
artificial intelligence
control system
orders of magnitude
position and orientation
relative position
non binary