Statements (29)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:appliesTo |
image classification
|
| gptkbp:author |
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:basedOn |
transformer architecture
|
| gptkbp:citation |
high
|
| gptkbp:developedBy |
gptkb:Google_Research
|
| gptkbp:fullName |
gptkb:Vision_Transformer
|
| https://www.w3.org/2000/01/rdf-schema#label |
ViT
|
| gptkbp:improves |
convolutional neural networks (on large datasets)
|
| gptkbp:input |
image patches
|
| gptkbp:inspiredBy |
subsequent vision transformer models
|
| gptkbp:introducedIn |
2020
|
| gptkbp:openSource |
gptkb:TensorFlow
gptkb:PyTorch |
| gptkbp:publishedIn |
gptkb:An_Image_is_Worth_16x16_Words:_Transformers_for_Image_Recognition_at_Scale
|
| gptkbp:uses |
self-attention mechanism
|
| gptkbp:bfsParent |
gptkb:Vision_Transformer
|
| gptkbp:bfsLayer |
6
|