|
gptkbp:instanceOf
|
self-supervised learning model
|
|
gptkbp:architecture
|
gptkb:Vision_Transformer
|
|
gptkbp:author
|
gptkb:Armand_Joulin
gptkb:Hugo_Touvron
gptkb:Piotr_Bojanowski
gptkb:Hervé_Jégou
gptkb:Gabriel_Synnaeve
gptkb:Matthieu_Cord
|
|
gptkbp:basedOn
|
gptkb:Vision_Transformer
|
|
gptkbp:category
|
computer vision model
|
|
gptkbp:developedBy
|
gptkb:Meta_AI
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
DINOv2
|
|
gptkbp:input
|
gptkb:illustrator
|
|
gptkbp:language
|
gptkb:Python
|
|
gptkbp:license
|
CC-BY-NC 4.0
|
|
gptkbp:memiliki_tugas
|
self-supervised learning
image representation learning
|
|
gptkbp:notableFeature
|
scalable to billions of images
state-of-the-art performance on several benchmarks
|
|
gptkbp:notablePublication
|
DINOv2: Learning Robust Visual Features without Supervision
|
|
gptkbp:openSource
|
true
|
|
gptkbp:output
|
image embedding
|
|
gptkbp:pdf
|
https://arxiv.org/abs/2304.07193
|
|
gptkbp:predecessor
|
gptkb:DINO
|
|
gptkbp:releaseDate
|
2023
|
|
gptkbp:repository
|
https://github.com/facebookresearch/dinov2
|
|
gptkbp:supports
|
few-shot learning
zero-shot learning
|
|
gptkbp:trainer
|
large-scale web images
|
|
gptkbp:usedFor
|
image classification
object detection
semantic segmentation
|
|
gptkbp:bfsParent
|
gptkb:Hugging_Face_models
gptkb:SAM_model
|
|
gptkbp:bfsLayer
|
7
|