Improve Vision Transformers Training by Suppressing Over-smoothing.

Chengyue Gong Dilin Wang Meng Li Vikas Chandra Qiang Liu

Published in: CoRR (2021)

Keyphrases

computer vision
preprocessing step
neural network
real world
online learning
database
data sets
databases
machine learning
high level
multiscale
hidden markov models
supervised learning
vision system
training phase
smoothing algorithm