1. Dropout: a simple way to prevent neural networks from overfitting;srivastava;J Mach Learn Res,2014
2. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift;ioffe,2015
3. U-Net: Convolutional Networks for Biomedical Image Segmentation;ronneberger;Med Image Comput Comput Interv – MICCAI 2015,2015
4. Multi-scale context aggregation by dilated convolutions;yu,2015
5. Enet: A deep neural network architecture for real-time semantic segmentation;paszke,2016