1. Efficient self-supervised vision transformers for representation learning;li;Proc Int Conf Learn Representations,2022
2. Training data-efficient image transformers & distillation through attention;touvron;Proc Int Conf Mach Learn,2021
3. MST: Masked self-supervised transformer for visual representation;li;Proc Adv Neural Inf Process Syst,2021
4. Mugs: A multi-granular self-supervised learning framework;zhou,2022
5. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions