computer-vision-study-group/Sessions/MaskedAutoEncoders.md

Masked Autoencoders are Scalable Vision Learners

Session by johko

Recording 📺

YouTube

Session Slides 🖥️

Google Drive

Original Paper 📄

Hugging Face / arxiv

GitHub Repo 🧑🏽‍💻

https://github.com/facebookresearch/mae

Additional Resources 📚

• Transformers Docs ViTMAE
• Transformers ViTMAE Demo Notebook by Niels Rogge