|
gptkbp:instance_of
|
gptkb:Model
|
|
gptkbp:applies_to
|
Image Classification
Object Detection
Semantic Segmentation
|
|
gptkbp:architectural_style
|
gptkb:Transformers_character
|
|
gptkbp:collaborated_with
|
Academic Institutions
Industry Partners
Open Source Communities
Research Labs
|
|
gptkbp:developed_by
|
gptkb:Microsoft_Research
|
|
gptkbp:has_achievements
|
State-of-the-art performance
|
|
gptkbp:has_method
|
50 million
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Swin-B
|
|
gptkbp:input_output
|
224x224
|
|
gptkbp:introduced
|
gptkb:2021
|
|
gptkbp:is_available_in
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_discussed_in
|
gptkb:Workshops
gptkb:conference
Conferences
Webinars
|
|
gptkbp:is_documented_in
|
Research Papers
Technical Reports
Git Hub Repositories
Documentation Websites
|
|
gptkbp:is_evaluated_by
|
gptkb:Cityscapes_Dataset
gptkb:COCO_Dataset
Top-1 Accuracy
Top-5 Accuracy
AD E20 K Dataset
m Io U
|
|
gptkbp:is_influenced_by
|
gptkb:television_channel
gptkb:Vision_Transformers
|
|
gptkbp:is_known_for
|
Efficiency
Flexibility
Scalability
|
|
gptkbp:is_optimized_for
|
Vision Tasks
|
|
gptkbp:is_part_of
|
Computer Vision Community
|
|
gptkbp:is_related_to
|
gptkb:Swin-L
gptkb:Swin-T
|
|
gptkbp:is_supported_by
|
Community Contributions
Open Source Projects
|
|
gptkbp:is_used_in
|
Research Papers
Industry Applications
|
|
gptkbp:part_of
|
Swin Transformer family
|
|
gptkbp:performance
|
gptkb:Efficient_Net
gptkb:Res_Net
gptkb:Swin_Transformer
gptkb:Vision_Transformers
Vision Models
|
|
gptkbp:supports
|
Multi-scale Representation
|
|
gptkbp:training
|
gptkb:Image_Net
Supervised Learning
Self-supervised Learning
|
|
gptkbp:uses
|
Attention Mechanism
Layer Normalization
Hierarchical Feature Maps
Shifted Windowing Scheme
|
|
gptkbp:bfsParent
|
gptkb:Swin_Transformer
|
|
gptkbp:bfsLayer
|
5
|