@article{trainingdataefficientimagetransformers, title = {Training data-efficient image transformers & distillation through attention}, author = {Hugo Touvron and Matthieu Cord and Matthijs Douze and Francisco Massa and Alexandre Sablayrolles and Hervé Jégou}, year = {2020}, eprint = {2012.12877}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2012.12877v2}, }