|
gptkbp:instance_of
|
gptkb:Model
|
|
gptkbp:bfsLayer
|
5
|
|
gptkbp:bfsParent
|
gptkb:Layout_LM
gptkb:Dei_T
gptkb:Vision_Transformers
|
|
gptkbp:applies_to
|
image classification
|
|
gptkbp:architectural_style
|
gptkb:Transformers_character
|
|
gptkbp:developed_by
|
gptkb:Google_Research
open-source collaboration
|
|
gptkbp:has_achievements
|
image recognition tasks
|
|
gptkbp:has_programs
|
gptkb:Photographer
gptkb:robot
gptkb:engine
augmented reality
security systems
|
|
gptkbp:has_variants
|
Vi T-B, Vi T-L, Vi T-H
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Vi T
|
|
gptkbp:introduced
|
gptkb:2020
|
|
gptkbp:is_adopted_by
|
universities
research institutions
startups
tech companies
|
|
gptkbp:is_cited_in
|
numerous research papers
|
|
gptkbp:is_compared_to
|
gptkb:Efficient_Net
gptkb:Dense_Net
gptkb:Res_Net
CN Ns
|
|
gptkbp:is_discussed_in
|
gptkb:academic_journal
|
|
gptkbp:is_evaluated_by
|
gptkb:CIFAR-10
gptkb:CIFAR-100
real-world scenarios
cross-validation
Food-101
ablation studies
Oxford Pets
|
|
gptkbp:is_explored_in
|
tutorials
workshops
online courses
webinars
|
|
gptkbp:is_implemented_in
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_influenced_by
|
gptkb:BERT
|
|
gptkbp:is_known_for
|
high accuracy
scalability
|
|
gptkbp:is_optimized_for
|
parallel processing
|
|
gptkbp:is_part_of
|
deep learning frameworks
AI research community
AI conferences
Vision Transformers family
|
|
gptkbp:is_related_to
|
transfer learning
self-supervised learning
|
|
gptkbp:is_supported_by
|
community contributions
NVIDIAGP Us
TP Us
|
|
gptkbp:is_used_in
|
object detection
facial recognition
image segmentation
scene understanding
computer vision applications
|
|
gptkbp:origin
|
new research findings
|
|
gptkbp:performance
|
using large datasets
vision tasks
|
|
gptkbp:requires
|
large computational resources
|
|
gptkbp:training
|
gptkb:Image_Net
data augmentation techniques
|
|
gptkbp:uses
|
self-attention mechanism
|