Do Vision Transformers See Like Convolutional Neural Networks?

Maithra Raghu Thomas Unterthiner Simon Kornblith Chiyuan Zhang Alexey Dosovitskiy

Published in: CoRR (2021)

Keyphrases

convolutional neural networks
convolutional network
vision system
real time
computer vision
active vision
information retrieval
data sets
facial landmark localization
image processing
web services
bayesian networks
visual perception
human vision
e learning
web pages
machine learning
neural network