changlin31 / AutoProg

(CVPR 2022) Automated Progressive Learning for Efficient Training of Vision Transformers

AutoProg

This project is used to update news related to our paper Automated Progressive Learning for Efficient Training of Vision Transformers (CVPR 2022).

AutoProg achieves efficient training by automatically increasing the training overload on-the-fly.

AutoProg can accelerate ViTs training by up to 85.1% with no performance drop.

Implementations

Code will be released soon.

Citation

If you use our code for your paper, please cite:

@inproceedings{li2022autoprog,
  author = {Li, Changlin and 
            Zhuang, Bohan and 
            Wang, Guangrun and
            Liang, Xiaodan and
            Chang, Xiaojun and
            Yang, Yi},
  title = {Automated Progressive Learning for Efficient Training of Vision Transformers},
  booktitle = {CVPR},
  year = 2022,
}