Better plain ViT baselines for ImageNet-1k.

Lucas Beyer Xiaohua Zhai Alexander Kolesnikov

Published in: CoRR (2022)

Keyphrases

image collections
hierarchical structure
million images
linear svm
multiscale
data mining
object categories
search engine
logistic regression
image processing
database systems
object recognition
training set
feature vectors
object detection
image search