반응형 [CV] CvT [출처] CvT: Introducing Convolutions to Vision Transformers [출처]: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 요약논문 제목: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale저자: Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly.. 2024. 6. 7. 반응형
