Data-efficient Image Transformer
GPTKB entity
Statements (23)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:convolutional_neural_network
vision transformer |
gptkbp:abbreviation |
gptkb:DeiT
|
gptkbp:author |
gptkb:Armand_Joulin
gptkb:Edouard_Grave gptkb:Hugo_Touvron gptkb:Hervé_Jégou gptkb:Gabriel_Synnaeve gptkb:Matthieu_Cord Alexandre Sablayrolles |
gptkbp:designedFor |
image classification
|
gptkbp:developedBy |
gptkb:Facebook_AI_Research
|
https://www.w3.org/2000/01/rdf-schema#label |
Data-efficient Image Transformer
|
gptkbp:improves |
Vision Transformer (ViT) with less data
|
gptkbp:introducedIn |
2020
|
gptkbp:notablePublication |
https://arxiv.org/abs/2012.12877
|
gptkbp:openSource |
yes
|
gptkbp:publishedIn |
gptkb:ICML_2021
|
gptkbp:repository |
https://github.com/facebookresearch/deit
|
gptkbp:uses |
transformer architecture
distillation token |
gptkbp:bfsParent |
gptkb:Vision_Transformer
|
gptkbp:bfsLayer |
6
|