reference

gistfile1.txt

@inproceedings{lin2017focal,
  title={Focal loss for dense object detection},
  author={Lin, Tsung-Yi and Goyal, Priya and Girshick, Ross and He, Kaiming and Doll{\'a}r, Piotr},
  booktitle={Proceedings of the IEEE international conference on computer vision},
  pages={2980--2988},
  year={2017}
}

@Article{paszke2017automatic,
title={Automatic differentiation in PyTorch},
author={Paszke, Adam and Gross, Sam and Chintala, Soumith and Chanan, Gregory and Yang, Edward and DeVito, Zachary and Lin, Zeming and Desmaison, Alban and Antiga, Luca and Lerer, Adam},
year={2017}
}

@inproceedings{ronneberger2015u,
title={U-net: Convolutional networks for biomedical image segmentation},
author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
booktitle={International Conference on Medical image computing and computer-assisted intervention},
pages={234--241},
year={2015},
organization={Springer}
}

@inproceedings{huang2016deep,
title={Deep networks with stochastic depth},
author={Huang, Gao and Sun, Yu and Liu, Zhuang and Sedra, Daniel and Weinberger, Kilian Q},
booktitle={European conference on computer vision},
pages={646--661},
year={2016},
organization={Springer}
}

@inproceedings{huang2017densely,
title={Densely connected convolutional networks},
author={Huang, Gao and Liu, Zhuang and Van Der Maaten, Laurens and Weinberger, Kilian Q},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={4700--4708},
year={2017}
}

@inproceedings{mnih2016asynchronous,
title={Asynchronous methods for deep reinforcement learning},
author={Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy and Harley, Tim and Silver, David and Kavukcuoglu, Koray},
booktitle={International conference on machine learning},
pages={1928--1937},
year={2016}
}

@Article{gu2016q,
title={Q-prop: Sample-efficient policy gradient with an off-policy critic},
author={Gu, Shixiang and Lillicrap, Timothy and Ghahramani, Zoubin and Turner, Richard E and Levine, Sergey},
journal={arXiv preprint arXiv:1611.02247},
year={2016}
}

@inproceedings{he2016identity,
title={Identity mappings in deep residual networks},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={European conference on computer vision},
pages={630--645},
year={2016},
organization={Springer}
}

@Article{hochreiter1997long,
title={Long short-term memory},
author={Hochreiter, Sepp and Schmidhuber, J{"u}rgen},
journal={Neural computation},
volume={9},
number={8},
pages={1735--1780},
year={1997},
publisher={MIT Press}
}

@inproceedings{huang2016deep,
title={Deep networks with stochastic depth},
author={Huang, Gao and Sun, Yu and Liu, Zhuang and Sedra, Daniel and Weinberger, Kilian Q},
booktitle={European conference on computer vision},
pages={646--661},
year={2016},
organization={Springer}
}

@Article{ioffe2015batch,
title={Batch normalization: Accelerating deep network training by reducing internal covariate shift},
author={Ioffe, Sergey and Szegedy, Christian},
journal={arXiv preprint arXiv:1502.03167},
year={2015}
}

@inproceedings{nair2010rectified,
title={Rectified linear units improve restricted boltzmann machines},
author={Nair, Vinod and Hinton, Geoffrey E},
booktitle={Proceedings of the 27th international conference on machine learning (ICML-10)},
pages={807--814},
year={2010}
}

@Article{santurkar2018does,
title={How does batch normalization help optimization?(no, it is not about internal covariate shift)},
author={Santurkar, Shibani and Tsipras, Dimitris and Ilyas, Andrew and Madry, Aleksander},
journal={arXiv preprint arXiv:1805.11604},
year={2018}
}