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}
}

@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}
}