1. Tokens-to-token vit: Training vision transformers from scratch on imagenet;li;ArXiv Preprint,2021
2. Unified perceptual parsing for scene understanding;xiao;Proceedings of the European Conference on Computer Vision (ECCV),0
3. CvT: Introducing Convolutions to Vision Transformers
4. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions