DNN-Quan.bib

% ==================================================================
%                      Quantization 
% ==================================================================
@inproceedings{SPEED-ICML2015-Gupta,
    title     = {Deep learning with limited numerical precision},
    author    = {Gupta, Suyog and Agrawal, Ankur and Gopalakrishnan, Kailash and Narayanan, Pritish},
    booktitle = icml,
    pages     = {1737--1746},
    year      = {2015},
}
@inproceedings{SPEED-ICML2016-Lin,
    title     = {Fixed point quantization of deep convolutional networks},
    author    = {Lin, Darryl and Talathi, Sachin and Annapureddy, Sreekanth},
    booktitle = icml,
    pages     = {2849--2858},
    year      = {2016},
}
@inproceedings{SPEED-ICLR2018-Khoram,
    title     = {Adaptive quantization of neural networks},
    author    = {Khoram, Soroosh and Li, Jing},
    booktitle = iclr,
    year      = {2018},
}
% ====== quantization + pruning
@inproceedings{SPEED-CVPR2018-CLIP-Q,
    title     = {{CLIP-Q}: Deep network compression learning by in-parallel pruning-quantization},
    author    = {Tung, Frederick and Mori, Greg},
    booktitle = cvpr,
    pages     = {7873--7882},
    year      = {2018},
}


% ==================================================================
%                   Binarized / Ternary 
% ==================================================================
% ==== during-training
@inproceedings{SPEED-ICLR2017-Zhu,
    title     = {Trained ternary quantization},
    author    = {Zhu, Chenzhuo and Han, Song and Mao, Huizi and Dally, William J.},
    booktitle = iclr,
    year      = {2017},
}
% ==== post-training
@inproceedings{SPEED-NIPS2015-Novikov,
    title     = {Tensorizing Neural Networks},
    author    = {Novikov, Alexander and Podoprikhin, Dmitry and Osokin, Anton and Vetrov, Dmitry},
    booktitle = nips,
    year      = {2015},
    pages     = {442--450},
}
@inproceedings{SPEED-ECCV2016-XNOR-NET,
    title     = {{XNOR-NET}: Imagenet classification using binary convolutional neural networks},
    author    = {Rastegari, Mohammad and Ordonez, Vicente and Redmon, Joseph and Farhadi, Ali},
    booktitle = eccv,
    pages     = {525--542},
    year      = {2016},
}
@inproceedings{SPEED-FPGA2017-Zhao,
    title     = {Accelerating binarized convolutional neural networks with software-programmable {FPGAs}},
    author    = {Zhao, Ritchie and Song, Weinan and Zhang, Wentao and Xing, Tianwei and Lin, Jeng-Hau and Srivastava, Mani and Gupta, Rajesh and Zhang, Zhiru},
    booktitle = fpga,
    pages     = {15--24},
    year      = {2017},
}
@inproceedings{SPEED-DAC2017-Kim,
    author    = {Kim, Hyeonuk and Sim, Jaehyeong and Choi, Yeongjae and Kim, Lee-Sup},
    title     = {A Kernel Decomposition Architecture for Binary-weight Convolutional Neural Networks},
    booktitle = dac,
    pages     = {60:1--60:6},
    year      = {2017},
}
@inproceedings{SPEED-ICMLW2019-DeepCABAC,
    title     = {{DeepCABAC}: Context-adaptive binary arithmetic coding for deep neural network compression},
    author    = {Wiedemann, Simon and Kirchhoffer, Heiner and Matlage, Stefan and Haase, Paul and Marban, Arturo and Marinc, Talmaj and Neumann, David and Osman, Ahmed and Marpe, Detlev and Schwarz, Heiko and others},
    booktitle = {ICML Workshop},
    year      = {2019},
}