(이 게시글은 나 참고용으로 대충 )[Submitted on 24 Mar 2021]https://arxiv.org/abs/2103.13413 Vision Transformers for Dense PredictionWe introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into image-like represearxiv.org https://githu..
