Swin-Small

Papers using or citing this model 1

• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 36.6K citations · 2021 · arXiv (Cornell University) · arXiv

  This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the...