maes
Masked Image Modeling
- BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers (2022-08-12)
- [2308.00566] Predicting masked tokens in stochastic locations improves masked image modeling
- GitHub - facebookresearch/maws: Code and models for the paper “The effectiveness of MAE pre-pretraining for billion-scale pretraining” https://arxiv.org/abs/2303.13496