Login / Signup
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet.
Li Yuan
Yunpeng Chen
Tao Wang
Weihao Yu
Yujun Shi
Francis E. H. Tay
Jiashi Feng
Shuicheng Yan
Published in:
CoRR (2021)
Keyphrases
</>
linear svm
computer vision
training process
image processing
training examples
vision system
supervised learning
classifier training
training set
object recognition
multiscale
real time
small number
database
image classification
hierarchical structure
machine learning
training phase
data sets
computer software