1、目的
探索visual tokenizer编码下的MIM（Masked Image Modeling）
2、方法
iBOT（i mage B ERT pre-training with O nline Tokenizer）
1）knowledge distillation（KD）
distill knowledge from the tokenizer
2）self-distillation
twin teacher as online tokenizer
3）visual tokenizer
-> transform the masked patches to supervisory signals for the target model
-> 通过enforce the similarity of cross-view images on class tokens，来捕获到high-level visual semantics
-> 无须额外的训练，通过momentum update来和MIM一同被优化
-> online，而不是pre-fixed
4）网络结构
-> 
，
-> 用softmax之后的token，而非ont-hot
5）multi-crop
6）MIM
3、结论
1）iBOT is more scalable to larger models
2）iBOT requires more data to train larger model