1. Masked autoencoders are scalable vision learners;He,2022
2. A unified view of masked image modeling;Peng;arXiv preprint arXiv:2210.10615,2022
3. ibot: Image bert pre-training with online tokenizer;Zhou;arXiv preprint arXiv:2111.07832,2021
4. Representation learning with contrastive predictive coding;Oord;arXiv preprint arXiv:1807.03748,2018
5. Momentum contrast for unsupervised visual representation learning;He,2020