facebookresearch/deit

@InProceedings{pmlr-v139-touvron21a,
  title =     {Training data-efficient image transformers & distillation through attention},
  author =    {Touvron, Hugo and Cord, Matthieu and Douze, Matthijs and Massa, Francisco and Sablayrolles, Alexandre and Jegou, Herve},
  booktitle = {International Conference on Machine Learning},
  pages =     {10347--10357},
  year =      {2021},
  volume =    {139},
  month =     {July}
}

@InProceedings{Touvron_2021_ICCV,
    author    = {Touvron, Hugo and Cord, Matthieu and Sablayrolles, Alexandre and Synnaeve, Gabriel and J\'egou, Herv\'e},
    title     = {Going Deeper With Image Transformers},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {32-42}
}

@article{touvron2021resmlp,
  title={ResMLP: Feedforward networks for image classification with data-efficient training},
  author={Hugo Touvron and Piotr Bojanowski and Mathilde Caron and Matthieu Cord and Alaaeldin El-Nouby and Edouard Grave and Gautier Izacard and Armand Joulin and Gabriel Synnaeve and Jakob Verbeek and Herv'e J'egou},
  journal={arXiv preprint arXiv:2105.03404},
  year={2021},
}

@article{touvron2021patchconvnet,
  title={Augmenting Convolutional networks with attention-based aggregation},
  author={Hugo Touvron and Matthieu Cord and Alaaeldin El-Nouby and Piotr Bojanowski and Armand Joulin and Gabriel Synnaeve and Jakob Verbeek and Herve Jegou},
  journal={arXiv preprint arXiv:2112.13692},
  year={2021},
}

@article{Touvron2022ThreeTE,
  title={Three things everyone should know about Vision Transformers},
  author={Hugo Touvron and Matthieu Cord and Alaaeldin El-Nouby and Jakob Verbeek and Herve Jegou},
  journal={arXiv preprint arXiv:2203.09795},
  year={2022},
}

@article{Touvron2022DeiTIR,
  title={DeiT III: Revenge of the ViT},
  author={Hugo Touvron and Matthieu Cord and Herve Jegou},
  journal={arXiv preprint arXiv:2204.07118},
  year={2022},
}

@article{Touvron2022Cotraining2S,
  title={Co-training 2L Submodels for Visual Recognition},
  author={Hugo Touvron and Matthieu Cord and Maxime Oquab and Piotr Bojanowski and Jakob Verbeek and Herv'e J'egou},
  journal={arXiv preprint arXiv:2212.04884},
  year={2022},
}