Storage-efficient Vision Training

This repository contains PyTorch training code and pretrained models for the following papers:

SeiT : Storage-efficient Vision Training, ICCV 2023.

SeiT++ : Masked Token Modeling Improves Storage-efficient Training, ECCV 2024.

If you find this repository useful, please consider giving a star ⭐ and cite the relevant papers.

Citation

@inproceedings{park2023seit,
    title={SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage},
    author={Park, Song and Chun, Sanghyuk and Heo, Byeongho and Kim, Wonjae and Yun, Sangdoo},
    year={2023},
    booktitle={International Conference on Computer Vision (ICCV)},
}

@article{lee2023seitpp,
  title={SeiT++: Masked Token Modeling Improves Storage-efficient Training},
  author={Lee, Minhyun and Park, Song and Heo, Byeongho and Han, Dongyoon and Shim, Hyunjung},
  journal={arXiv preprint arXiv:2312.10105},
  year={2023}
}

License

SeiT++
Copyright (c) 2024-present NAVER Cloud Corp.
CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)