// ◐ World Models & Self-Supervised Learning
Masked Autoencoders (MAE)
Masks 75% of image patches and reconstructs them to learn representations.
掩码自编码器 MAE 2021 Intermediate core
IN PLAIN WORDS
BERT-style masking for vision: the encoder sees only visible patches and a light decoder reconstructs the rest. High masking makes the task hard yet training fast.
Used in: Visual pretraining, medical imaging
TIMELINE · prerequisites → this → what builds on it
01Original paper
Masked Autoencoders Are Scalable Vision Learners
Kaiming He, Xinlei Chen, Saining Xie, et al. · 2021
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
Related:SimCLR
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Reference code
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
mae)