> ML_ARCHITECTURE // SWIN-TRANSFORMER-HIERARCHICAL_v1.0
Swin Transformer (Hierarchical Shifted Window Transformer)
Hierarchical vision transformer computing self-attention within local shifted windows, delivering linear computational complexity with respect to image resolution for dense prediction.
Vision Transformersimage
Back to All ArchitecturesArchitecture Overview
Hierarchical vision transformer computing self-attention within local shifted windows, delivering linear computational complexity with respect to image resolution for dense prediction.
Implementing Libraries
Seminal Papers
Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin (2021) · IEEE International Conference on Computer Vision (ICCV)
Architectural Limitations & Constraints
- Requires compatible deep learning framework and hardware acceleration for efficient execution.