Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Presents Swin Transformer, a hierarchical vision Transformer using shifted windows as a general-purpose vision backbone.
Adapting Transformers from language to vision is hard because visual entities vary greatly in scale and images have far higher pixel resolution than text has words. Swin Transformer addresses this with a hierarchical architecture using shifted windows, limiting self-attention to non-overlapping local windows while allowing cross-window connections, giving linear complexity in image size. As a general-purpose backbone it reaches 87.3% top-1 on ImageNet-1K, 58.7 box AP and 51.1 mask AP on COCO, and 53.5 mIoU on ADE20K, surpassing prior state of the art by wide margins.
Based on: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows · IEEE International Conference on Computer Vision
Curated by Aramai Editorial
Read summary →