1. Rethinking the inception architecture for computer vision;szegedy;arXiv 1512 00567 [cs],2015
2. Adam: A method for stochastic optimization;kingma;arXiv 1412 6980,2014
3. Dropout: A simple way to prevent neural networks from overfitting;srivastava;J Mach Learn Res,2019
4. No subclass left behind: Fine-grained robustness in coarse-grained classification problems;sohoni;arXiv 2011 12945,2020