some papers to add

[fawazsammani]

• Escaping the Big Data Paradigm with Compact Transformers: https://arxiv.org/pdf/2104.05704.pdf
• How to train your ViT? Data, Augmentation,and Regularization in Vision Transformers: https://arxiv.org/pdf/2106.10270.pdf
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks: https://arxiv.org/pdf/2105.02358.pdf

[dk-liang]

added