@inproceedings{dl-08-1,
  title = {{An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}},
  author = {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  booktitle = {International Conference on Learning Representations},
  year = {2021},
  url = {https://arxiv.org/abs/2010.11929}
}

@inproceedings{dl-08-2,
  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 Jégou, Hervé},
  booktitle = {Proceedings of the 38th International Conference on Machine Learning},
  year = {2021},
  url = {https://proceedings.mlr.press/v139/touvron21a.html}
}

@misc{dl-08-3,
  title = {{Swin Transformer: Hierarchical Vision Transformer using Shifted Windows}},
  author = {Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  howpublished = {arXiv},
  year = {2021},
  doi = {10.48550/arXiv.2103.14030},
  url = {https://arxiv.org/abs/2103.14030}
}