Statements (31)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:model
vision transformer |
gptkbp:abbreviation |
gptkb:PVT
|
gptkbp:application |
image classification
object detection semantic segmentation |
gptkbp:architecture |
hierarchical transformer
|
gptkbp:arXivID |
2102.12122
|
gptkbp:author |
gptkb:Xiaogang_Wang
gptkb:Yun_Liu gptkb:Tianheng_Cheng gptkb:Jifeng_Dai gptkb:Ziwei_Liu Huiyu Wang Jiaming Sun Yanghao Li Yukun Zhu |
gptkbp:feature |
pyramid structure
multi-scale feature representation spatial reduction attention |
gptkbp:field |
gptkb:machine_learning
computer vision |
https://www.w3.org/2000/01/rdf-schema#label |
Pyramid Vision Transformer
|
gptkbp:improves |
gptkb:ResNet
gptkb:Vision_Transformer |
gptkbp:inspiredBy |
gptkb:Vision_Transformer
|
gptkbp:introducedIn |
2021
|
gptkbp:openSource |
yes
|
gptkbp:publishedIn |
gptkb:arXiv
|
gptkbp:bfsParent |
gptkb:Vision_Transformer
|
gptkbp:bfsLayer |
6
|