AI 공부 한 것
[논문 리뷰] ViT (AN IMAGE IS WORTH 16X16 WORDS:TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE)
아무것도모르는사람
2023. 2. 7. 13:51
https://arxiv.org/abs/2010.11929
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to rep
arxiv.org
(Inductive Bias란 학습 시에는 만나보지 않았던 상황에 대하여 정확한 예측을 하기 위해 사용하는 추가적인 가정을 의미합니다.)