Machine learningDeep Learning, Vision Transformers
Swin Transformer
Swin Transformer 是由 Liu 等人于 2021 年提出的一种分层视觉 Transformer 模型，它使用移位窗口注意力机制，在保持计算机视觉任务强大性能的同时实现了计算效率。与原始的 Vision Transformer 应用全局自注意力不同，Swin 使用基于局部窗口的注意力并通过周期性移位来平衡表达能力和效率。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10012-10022). DOI: 10.1109/ICCV48922.2021.00986 ↗
如何引用本页
ScholarGate. (2026, June 3). Shifted Window Transformer for Vision. ScholarGate. https://scholargate.app/zh/deep-learning/swin-transformer
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →