1. CvT: Introducing Convolutions to Vision Transformers
2. Scene-former: Indoor scene generation with transformers;wang;CoRR,2020
3. Training data-efficient image transformers & distillation through attention;touvron;CoRR,2020
4. Efficientnet: Rethinking model scaling for convolutional neural networks;tan;CoRR,2019
5. Going deeper with convolutions;szegedy;CoRR,2014