PaperICCV 2021 · 2021
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
1page built on it
0more pages cite it
0narratives
0registry papers cite it
In the Atlas
ModelPrimary source of
Swin Transformer
Hierarchical vision transformer with shifted-window attention: linear complexity in image area, CNN-style multi-scale feature maps, and a drop-in backbone for dense prediction — with relative position bias replacing absolute embeddings.
Lineage
Papers in the Atlas registry only · one dot per paperBuilt upon by · 0
Builds on · 4
2016Deep Residual Learning for Image RecognitionHe, Zhang et al.2017Attention Is All You NeedVaswani, Shazeer et al.2020An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleDosovitskiy, Beyer et al.2020Training data-efficient image transformers & distillation through attentionTouvron, Cord et al.Built upon by · 0