|
gptkbp:instanceOf
|
gptkb:model
gptkb:convolutional_neural_network
|
|
gptkbp:abbreviation
|
gptkb:ViT
|
|
gptkbp:appliesTo
|
image classification
|
|
gptkbp:arXivID
|
2010.11929
|
|
gptkbp:basedOn
|
transformer architecture
|
|
gptkbp:citation
|
over 10,000 (as of 2024)
|
|
gptkbp:developedBy
|
gptkb:Google_Research
|
|
gptkbp:hasVariant
|
gptkb:Compact_Vision_Transformer
gptkb:CvT
gptkb:Data-efficient_Image_Transformer
gptkb:DeiT
gptkb:MobileViT
gptkb:Pyramid_Vision_Transformer
gptkb:Swin_Transformer
gptkb:T2T-ViT
gptkb:ViT-B
gptkb:ViT-G
gptkb:ViT-H
gptkb:ViT-L
gptkb:ViT-M
gptkb:ViT-S
gptkb:ViT-T
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Vision Transformer
|
|
gptkbp:improves
|
convolutional neural networks (on large datasets)
|
|
gptkbp:input
|
image patches
|
|
gptkbp:inspiredBy
|
subsequent vision transformer models
|
|
gptkbp:introduced
|
gptkb:Alexey_Dosovitskiy
gptkb:Jakob_Uszkoreit
gptkb:Alexander_Kolesnikov
gptkb:Dirk_Weissenborn
gptkb:Georg_Heigold
gptkb:Lucas_Beyer
gptkb:Matthias_Minderer
gptkb:Mostafa_Dehghani
gptkb:Neil_Houlsby
gptkb:Sylvain_Gelly
gptkb:Thomas_Unterthiner
gptkb:Xiaohua_Zhai
|
|
gptkbp:introducedIn
|
2020
|
|
gptkbp:openSource
|
gptkb:TensorFlow
gptkb:PyTorch
|
|
gptkbp:publishedIn
|
gptkb:arXiv
|
|
gptkbp:trainer
|
gptkb:JFT-300M
gptkb:ImageNet
|
|
gptkbp:usedIn
|
medical imaging
object detection
semantic segmentation
video understanding
|
|
gptkbp:uses
|
self-attention mechanism
|
|
gptkbp:bfsParent
|
gptkb:transformation
gptkb:convolutional_neural_network
|
|
gptkbp:bfsLayer
|
5
|