반응형
논문 링크입니다.
https://arxiv.org/abs/2103.14030
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
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 two domains, such as
arxiv.org
2021년 발행
반응형
'AI > 논문리뷰' 카테고리의 다른 글
| [Detection] Focal Loss 논문 리뷰 (0) | 2022.06.05 |
|---|---|
| [Segmentation] RMI loss 논문 리뷰 (0) | 2022.06.05 |
| [NLP] 트랜스포머 논문 리뷰 (0) | 2022.06.01 |
| [Segmentation] U-Net 논문 리뷰 (0) | 2022.06.01 |
| [Segmentation] TransUnet 논문 리뷰 (0) | 2022.05.29 |