Statements (24)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:model
|
| gptkbp:architecture |
gptkb:transformation
|
| gptkbp:arXivID |
2106.08254
|
| gptkbp:author |
gptkb:Furu_Wei
gptkb:Hangbo_Bao gptkb:Li_Dong |
| gptkbp:basedOn |
gptkb:Vision_Transformer
|
| gptkbp:citation |
BEiT: BERT Pre-Training of Image Transformers
|
| gptkbp:developedBy |
gptkb:Microsoft_Research
|
| gptkbp:fullName |
Bidirectional Encoder representation from Image Transformers
|
| gptkbp:improves |
self-supervised learning for vision
|
| gptkbp:input |
images
|
| gptkbp:introducedIn |
2021
|
| gptkbp:language |
gptkb:Python
|
| gptkbp:license |
gptkb:MIT_License
|
| gptkbp:openSource |
true
|
| gptkbp:pretrainingMethod |
masked image modeling
|
| gptkbp:publishedIn |
gptkb:arXiv
|
| gptkbp:relatedTo |
gptkb:BERT
|
| gptkbp:usedFor |
computer vision
image classification |
| gptkbp:bfsParent |
gptkb:Hugging_Face_models
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
BEiT
|