Skip to content
Snippets Groups Projects
README.md 3.91 KiB
Newer Older
Hugo Touvron's avatar
Hugo Touvron committed
# Data-Efficient architectures and training for Image classification
Francisco Massa's avatar
Francisco Massa committed

Hugo Touvron's avatar
Hugo Touvron committed
This repository contains PyTorch evaluation code, training code and pretrained models for the following papers:
<details>
<summary>
  <a href="README_deit.md">DeiT</a> Data-Efficient Image Transformers, ICML 2021 [<b>bib</b>]
</summary>
Francisco Massa's avatar
Francisco Massa committed

```
rv's avatar
rv committed
@InProceedings{pmlr-v139-touvron21a,
rv's avatar
rv committed
  title =     {Training data-efficient image transformers &amp; distillation through attention},
rv's avatar
rv committed
  author =    {Touvron, Hugo and Cord, Matthieu and Douze, Matthijs and Massa, Francisco and Sablayrolles, Alexandre and Jegou, Herve},
  booktitle = {International Conference on Machine Learning},
rv's avatar
rv committed
  pages =     {10347--10357},
  year =      {2021},
  volume =    {139},
  month =     {July}
Francisco Massa's avatar
Francisco Massa committed
}
```
Hugo Touvron's avatar
Hugo Touvron committed
</details>
Hugo Touvron's avatar
Hugo Touvron committed
<a href="README_cait.md">CaiT</a> (Going deeper with Image Transformers), ICCV 2021  [<b>bib</b>]
Hugo Touvron's avatar
Hugo Touvron committed
@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}
}
Hugo Touvron's avatar
Hugo Touvron committed
<a href="README_resmlp.md">ResMLP</a> (ResMLP: Feedforward networks for image classification with data-efficient training), TPAMI 2022 [<b>bib</b>]
Hugo Touvron's avatar
Hugo Touvron committed
@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},
}
Hugo Touvron's avatar
Hugo Touvron committed
<a href="README_patchconvnet.md">PatchConvnet</a> (Augmenting Convolutional networks with attention-based aggregation) [<b>bib</b>]
Hugo Touvron's avatar
Hugo Touvron committed
@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},
}
Hugo Touvron's avatar
Hugo Touvron committed
<a href="README_3things.md">3Things</a> (Three things everyone should know about Vision Transformers), ECCV 2022 [<b>bib</b>]
Hugo Touvron's avatar
Hugo Touvron committed
@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},
}
<details>
<summary>
Hugo Touvron's avatar
Hugo Touvron committed
<a href="README_revenge.md">DeiT III</a> (DeiT III: Revenge of the ViT), ECCV 2022 [<b>bib</b>]
Hugo Touvron's avatar
Hugo Touvron committed
@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},
}
Hugo Touvron's avatar
Hugo Touvron committed
<details>
<summary>
<a href="README_cosub.md">Cosub</a> (Co-training 2L Submodels for Visual Recognition), CVPR 2023 [<b>bib</b>]
</summary>
Hugo Touvron's avatar
Hugo Touvron committed
```
@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},
}
```
</details>
Hugo Touvron's avatar
Hugo Touvron committed
If you find this repository useful, please consider giving a star ⭐ and cite the relevant papers. 
Francisco Massa's avatar
Francisco Massa committed
# License
This repository is released under the Apache 2.0 license as found in the [LICENSE](LICENSE) file.
Francisco Massa's avatar
Francisco Massa committed

# Contributing
We actively welcome your pull requests! Please see [CONTRIBUTING.md](.github/CONTRIBUTING.md) and [CODE_OF_CONDUCT.md](.github/CODE_OF_CONDUCT.md) for more info.