https://arxiv.org/abs/2103.14030 Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsThis 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 asarxiv.org이번 포스팅은 2021 ICCV에 accept된 Sw..

2024.09.10 - [Paper Review] - [논문] Segmentation이번 posting에서는 NLP에서 성능이 매우 좋다는 것이 증명된 Transformer를 vision task로 가져온 논문 3편에 대해 요약을 할 것이다.ViT [Vision Transformer]https://arxiv.org/abs/2010.11929[An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleWhile the Transformer architecture has become the de-fact..