Backbone ImageNet Classification with Deep Convolutional Neural Networks. NIPS 2012 Very Deep Convolutional Networks for Large-Scale Image Recognition. ICLR 2015 Deep Residual Learning for Image Recognition. CVPR 2016 Normalization Layer Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML 2015 Group Normalization. ECCV 2018 Attention Mechanism Attention Is All You Need. NIPS 2017