Running main-hf.py will train a Huggingface ViT model using DINO.
If you find this useful, please consider staring this repository or citing this implementation
@misc{mandalhfdino,
author = {Paul K. Mandal},
title = {A Huggingface Compatible Distillation with No Labels Implementation},
year = {2023},
month = {December},
note = {\url{https://github.com/PaulKMandal/huggingface-dino/}},
}
You should also cite the original implementation
@inproceedings{caron2021emerging,
title={Emerging Properties in Self-Supervised Vision Transformers},
author={Caron, Mathilde and Touvron, Hugo and Misra, Ishan and J\'egou, Herv\'e and Mairal, Julien and Bojanowski, Piotr and Joulin, Armand},
booktitle={Proceedings of the International Conference on Computer Vision (ICCV)},
year={2021}
}