longlian/CrossMAE

CrossMAE: Rethinking Patch Dependence for Masked Autoencoders

by Letian Fu*, Long Lian*, Renhao Wang, Baifeng Shi, Xudong Wang, Adam Yala†, Trevor Darrell†, Alexei A. Efros†, Ken Goldberg† at UC Berkeley and UCSF

[Paper] | [Project Page] | [Citation]

This repo has the models for CrossMAE: Rethinking Patch Dependence for Masked Autoencoders.

Please take a look at the GitHub repo to see instructions on pretraining, fine-tuning, and evaluation with these models.

	ViT-Small	ViT-Base	ViT-Base448	ViT-Large	ViT-Huge
pretrained checkpoint	download	download	download	download	download
fine-tuned checkpoint	download	download	download	download	download
Reference ImageNet accuracy (ours)	79.318	83.722	84.598	85.432	86.256
MAE ImageNet accuracy (baseline)			84.8		85.9

Citation

Please give us a star 🌟 on Github to support us!

Please cite our work if you find our work inspiring or use our code in your work:

@article{
    fu2025rethinking,
    title={Rethinking Patch Dependence for Masked Autoencoders},
    author={Letian Fu and Long Lian and Renhao Wang and Baifeng Shi and XuDong Wang and Adam Yala and Trevor Darrell and Alexei A Efros and Ken Goldberg},
    journal={Transactions on Machine Learning Research},
    issn={2835-8856},
    year={2025},
    url={https://openreview.net/forum?id=JT2KMuo2BV},
    note={}
}