references.bib

@article{odena2016deconvolution,
  author = {Odena, Augustus and Dumoulin, Vincent and Olah, Chris},
  title = {Deconvolution and Checkerboard Artifacts},
  journal = {Distill},
  year = {2016},
  url = {http://distill.pub/2016/deconv-checkerboard},
  doi = {10.23915/distill.00003}
}

@article{Collobert2017Wav2LetterAE,
  title={Wav2Letter: an End-to-End ConvNet-based Speech Recognition System},
  author={Ronan Collobert and Christian Puhrsch and Gabriel Synnaeve},
  journal={CoRR},
  year={2017},
  volume={abs/1609.03193}
}

@inproceedings{Deniz2018SegmentationOT,
  title={Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks},
  author={Cem M. Deniz and Spencer Hallyburton and Arakua Welbeck and Stephen Honig and Kyunghyun Cho and Gregory Chang},
  booktitle={Scientific Reports},
  year={2018}
}

@article{jain2010,
title = "Machines that learn to segment images: a crucial technology for connectomics",
journal = "Current Opinion in Neurobiology",
volume = "20",
number = "5",
pages = "653 - 666",
year = "2010",
note = "Neuronal and glial cell biology – New technologies",
issn = "0959-4388",
doi = "https://doi.org/10.1016/j.conb.2010.07.004",
url = "http://www.sciencedirect.com/science/article/pii/S0959438810001121",
author = "Viren Jain and H Sebastian Seung and Srinivas C Turaga",
abstract = "Connections between neurons can be found by checking whether synapses exist at points of contact, which in turn are determined by neural shapes. Finding these shapes is a special case of image segmentation, which is laborious for humans and would ideally be performed by computers. New metrics properly quantify the performance of a computer algorithm using its disagreement with ‘true’ segmentations of example images. New machine learning methods search for segmentation algorithms that minimize such metrics. These advances have reduced computer errors dramatically. It should now be faster for a human to correct the remaining errors than to segment an image manually. Further reductions in human effort are expected, and crucial for finding connectomes more complex than that of Caenorhabditis elegans."
}

@article{Esteva2017DermatologistlevelCO,
  title={Dermatologist-level classification of skin cancer with deep neural networks},
  author={Andre Esteva and Brett Kuprel and Roberto A. Novoa and Justin Ko and Susan M. Swetter and Helen M. Blau and Sebastian Thrun},
  journal={Nature},
  year={2017},
  volume={542},
  pages={115-118}
}

@article{braintumor2018,
author = {Albadawy, Ehab and Saha, Ashirbani and Mazurowski, Maciej},
year = {2018},
month = {01},
pages = {},
title = {Deep learning for segmentation of brain tumors: Impact of cross-institutional training and testing},
volume = {45},
journal = {Medical Physics},
doi = {10.1002/mp.12752}
}

@InProceedings{unet,
author="Ronneberger, Olaf
and Fischer, Philipp
and Brox, Thomas",
editor="Navab, Nassir
and Hornegger, Joachim
and Wells, William M.
and Frangi, Alejandro F.",
title="U-Net: Convolutional Networks for Biomedical Image Segmentation",
booktitle="Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015",
year="2015",
publisher="Springer International Publishing",
address="Cham",
pages="234--241",
abstract="There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net.",
isbn="978-3-319-24574-4"
}

@article{qi2017pointnet,
  title={PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation},
  author={Qi, Charles R and Su, Hao and Mo, Kaichun and Guibas, Leonidas J},
  journal={Proc. Computer Vision and Pattern Recognition (CVPR), IEEE},
  year={2017}
}


@article{Farabet:2013:LHF:2498740.2498895,
 author = {Farabet, Clement and Couprie, Camille and Najman, Laurent and LeCun, Yann},
 title = {Learning Hierarchical Features for Scene Labeling},
 journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
 issue_date = {August 2013},
 volume = {35},
 number = {8},
 month = aug,
 year = {2013},
 issn = {0162-8828},
 pages = {1915--1929},
 numpages = {15},
 url = {http://dx.doi.org/10.1109/TPAMI.2012.231},
 doi = {10.1109/TPAMI.2012.231},
 acmid = {2498895},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
 keywords = {Feature extraction,Image segmentation,Labeling,Vectors,Context,Image edge detection,Accuracy,scene parsing,Convolutional networks,deep learning,image segmentation,image classification},
} 

@article{DBLP:journals/corr/abs-1301-3572,
  author    = {Camille Couprie and
               Cl{\'{e}}ment Farabet and
               Laurent Najman and
               Yann LeCun},
  title     = {Indoor Semantic Segmentation using depth information},
  journal   = {CoRR},
  volume    = {abs/1301.3572},
  year      = {2013},
  url       = {http://arxiv.org/abs/1301.3572},
  archivePrefix = {arXiv},
  eprint    = {1301.3572},
  timestamp = {Mon, 13 Aug 2018 16:48:30 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1301-3572},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{Krizhevsky:2012:ICD:2999134.2999257,
 author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},
 title = {ImageNet Classification with Deep Convolutional Neural Networks},
 booktitle = {Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1},
 series = {NIPS'12},
 year = {2012},
 location = {Lake Tahoe, Nevada},
 pages = {1097--1105},
 numpages = {9},
 url = {http://dl.acm.org/citation.cfm?id=2999134.2999257},
 acmid = {2999257},
 publisher = {Curran Associates Inc.},
 address = {USA},
} 

@article{DBLP:journals/corr/SimonyanVZ13,
  author    = {Karen Simonyan and
               Andrea Vedaldi and
               Andrew Zisserman},
  title     = {Deep Inside Convolutional Networks: Visualising Image Classification
               Models and Saliency Maps},
  journal   = {CoRR},
  volume    = {abs/1312.6034},
  year      = {2013},
  url       = {http://arxiv.org/abs/1312.6034},
  archivePrefix = {arXiv},
  eprint    = {1312.6034},
  timestamp = {Mon, 13 Aug 2018 16:49:09 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/SimonyanVZ13},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/SzegedyLJSRAEVR14,
  author    = {Christian Szegedy and
               Wei Liu and
               Yangqing Jia and
               Pierre Sermanet and
               Scott E. Reed and
               Dragomir Anguelov and
               Dumitru Erhan and
               Vincent Vanhoucke and
               Andrew Rabinovich},
  title     = {Going Deeper with Convolutions},
  journal   = {CoRR},
  volume    = {abs/1409.4842},
  year      = {2014},
  url       = {http://arxiv.org/abs/1409.4842},
  archivePrefix = {arXiv},
  eprint    = {1409.4842},
  timestamp = {Mon, 13 Aug 2018 16:48:52 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/SzegedyLJSRAEVR14},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/HeZRS15,
  author    = {Kaiming He and
               Xiangyu Zhang and
               Shaoqing Ren and
               Jian Sun},
  title     = {Deep Residual Learning for Image Recognition},
  journal   = {CoRR},
  volume    = {abs/1512.03385},
  year      = {2015},
  url       = {http://arxiv.org/abs/1512.03385},
  archivePrefix = {arXiv},
  eprint    = {1512.03385},
  timestamp = {Mon, 13 Aug 2018 16:46:56 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/HeZRS15},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/HuangLW16a,
  author    = {Gao Huang and
               Zhuang Liu and
               Kilian Q. Weinberger},
  title     = {Densely Connected Convolutional Networks},
  journal   = {CoRR},
  volume    = {abs/1608.06993},
  year      = {2016},
  url       = {http://arxiv.org/abs/1608.06993},
  archivePrefix = {arXiv},
  eprint    = {1608.06993},
  timestamp = {Mon, 10 Sep 2018 15:49:32 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/HuangLW16a},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-1805-00932,
  author    = {Dhruv Mahajan and
               Ross B. Girshick and
               Vignesh Ramanathan and
               Kaiming He and
               Manohar Paluri and
               Yixuan Li and
               Ashwin Bharambe and
               Laurens van der Maaten},
  title     = {Exploring the Limits of Weakly Supervised Pretraining},
  journal   = {CoRR},
  volume    = {abs/1805.00932},
  year      = {2018},
  url       = {http://arxiv.org/abs/1805.00932},
  archivePrefix = {arXiv},
  eprint    = {1805.00932},
  timestamp = {Mon, 13 Aug 2018 16:46:07 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1805-00932},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{Chopra:2005:LSM:1068507.1068961,
 author = {Chopra, Sumit and Hadsell, Raia and LeCun, Yann},
 title = {Learning a Similarity Metric Discriminatively, with Application to Face Verification},
 booktitle = {Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01},
 series = {CVPR '05},
 year = {2005},
 isbn = {0-7695-2372-2},
 pages = {539--546},
 numpages = {8},
 url = {http://dx.doi.org/10.1109/CVPR.2005.202},
 doi = {10.1109/CVPR.2005.202},
 acmid = {1068961},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
} 

@inproceedings { hadsell-chopra-lecun-06,
original = "orig/hadsell-chopra-lecun-06.pdf",
author = "Hadsell, Raia and Chopra, Sumit and LeCun, Yann",
title = "Dimensionality Reduction by Learning an Invariant Mapping",
booktitle = "Proc. Computer Vision and Pattern Recognition Conference (CVPR'06)",
publisher = "IEEE Press",
year = 2006,
note = "<a href='http://youtu.be/jcREIboRkn0'>Video</a>"
}

@article{DBLP:journals/corr/GirshickDDM13,
  author    = {Ross B. Girshick and
               Jeff Donahue and
               Trevor Darrell and
               Jitendra Malik},
  title     = {Rich feature hierarchies for accurate object detection and semantic
               segmentation},
  journal   = {CoRR},
  volume    = {abs/1311.2524},
  year      = {2013},
  url       = {http://arxiv.org/abs/1311.2524},
  archivePrefix = {arXiv},
  eprint    = {1311.2524},
  timestamp = {Mon, 13 Aug 2018 16:48:09 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/GirshickDDM13},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/RedmonDGF15,
  author    = {Joseph Redmon and
               Santosh Kumar Divvala and
               Ross B. Girshick and
               Ali Farhadi},
  title     = {You Only Look Once: Unified, Real-Time Object Detection},
  journal   = {CoRR},
  volume    = {abs/1506.02640},
  year      = {2015},
  url       = {http://arxiv.org/abs/1506.02640},
  archivePrefix = {arXiv},
  eprint    = {1506.02640},
  timestamp = {Mon, 13 Aug 2018 16:48:08 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/RedmonDGF15},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/PinheiroCD15,
  author    = {Pedro H. O. Pinheiro and
               Ronan Collobert and
               Piotr Doll{\'{a}}r},
  title     = {Learning to Segment Object Candidates},
  journal   = {CoRR},
  volume    = {abs/1506.06204},
  year      = {2015},
  url       = {http://arxiv.org/abs/1506.06204},
  archivePrefix = {arXiv},
  eprint    = {1506.06204},
  timestamp = {Mon, 13 Aug 2018 16:49:08 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/PinheiroCD15},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/HeGDG17,
  author    = {Kaiming He and
               Georgia Gkioxari and
               Piotr Doll{\'{a}}r and
               Ross B. Girshick},
  title     = {Mask {R-CNN}},
  journal   = {CoRR},
  volume    = {abs/1703.06870},
  year      = {2017},
  url       = {http://arxiv.org/abs/1703.06870},
  archivePrefix = {arXiv},
  eprint    = {1703.06870},
  timestamp = {Mon, 13 Aug 2018 16:46:36 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/HeGDG17},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-1708-02002,
  author    = {Tsung{-}Yi Lin and
               Priya Goyal and
               Ross B. Girshick and
               Kaiming He and
               Piotr Doll{\'{a}}r},
  title     = {Focal Loss for Dense Object Detection},
  journal   = {CoRR},
  volume    = {abs/1708.02002},
  year      = {2017},
  url       = {http://arxiv.org/abs/1708.02002},
  archivePrefix = {arXiv},
  eprint    = {1708.02002},
  timestamp = {Mon, 13 Aug 2018 16:46:12 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1708-02002},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-1809-01995,
  author    = {Natalia Neverova and
               Riza Alp G{\"{u}}ler and
               Iasonas Kokkinos},
  title     = {Dense Pose Transfer},
  journal   = {CoRR},
  volume    = {abs/1809.01995},
  year      = {2018},
  url       = {http://arxiv.org/abs/1809.01995},
  archivePrefix = {arXiv},
  eprint    = {1809.01995},
  timestamp = {Fri, 05 Oct 2018 11:34:52 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1809-01995},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/VaswaniSPUJGKP17,
  author    = {Ashish Vaswani and
               Noam Shazeer and
               Niki Parmar and
               Jakob Uszkoreit and
               Llion Jones and
               Aidan N. Gomez and
               Lukasz Kaiser and
               Illia Polosukhin},
  title     = {Attention Is All You Need},
  journal   = {CoRR},
  volume    = {abs/1706.03762},
  year      = {2017},
  url       = {http://arxiv.org/abs/1706.03762},
  archivePrefix = {arXiv},
  eprint    = {1706.03762},
  timestamp = {Mon, 13 Aug 2018 16:48:37 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/VaswaniSPUJGKP17},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/VinyalsTBE16,
  author    = {Oriol Vinyals and
               Alexander Toshev and
               Samy Bengio and
               Dumitru Erhan},
  title     = {Show and Tell: Lessons learned from the 2015 {MSCOCO} Image Captioning
               Challenge},
  journal   = {CoRR},
  volume    = {abs/1609.06647},
  year      = {2016},
  url       = {http://arxiv.org/abs/1609.06647},
  archivePrefix = {arXiv},
  eprint    = {1609.06647},
  timestamp = {Mon, 13 Aug 2018 16:48:21 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/VinyalsTBE16},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@misc{1211.5063,
Author = {Razvan Pascanu and Tomas Mikolov and Yoshua Bengio},
Title = {On the difficulty of training Recurrent Neural Networks},
Year = {2012},
Eprint = {arXiv:1211.5063},
}

@misc{1406.1078,
Author = {Kyunghyun Cho and Bart van Merrienboer and Caglar Gulcehre and Dzmitry Bahdanau and Fethi Bougares and Holger Schwenk and Yoshua Bengio},
Title = {Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation},
Year = {2014},
Eprint = {arXiv:1406.1078},
}

@article{article-lstm,
author = {Hochreiter, Sepp and Schmidhuber, Jürgen},
year = {1997},
month = {12},
pages = {1735-80},
title = {Long Short-term Memory},
volume = {9},
journal = {Neural computation},
doi = {10.1162/neco.1997.9.8.1735}
}

@inproceedings{gal2016dropout,
  title={Dropout as a bayesian approximation: Representing model uncertainty in deep learning},
  author={Gal, Yarin and Ghahramani, Zoubin},
  booktitle={international conference on machine learning},
  pages={1050--1059},
  year={2016}
}

@article{DBLP:journals/corr/abs-1902-06705,
  author    = {Nicholas Carlini and
               Anish Athalye and
               Nicolas Papernot and
               Wieland Brendel and
               Jonas Rauber and
               Dimitris Tsipras and
               Ian J. Goodfellow and
               Aleksander Madry and
               Alexey Kurakin},
  title     = {On Evaluating Adversarial Robustness},
  journal   = {CoRR},
  volume    = {abs/1902.06705},
  year      = {2019},
  url       = {http://arxiv.org/abs/1902.06705},
  archivePrefix = {arXiv},
  eprint    = {1902.06705},
  timestamp = {Sat, 02 Mar 2019 00:00:00 +0100},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1902-06705},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{glorot2010understanding,
  title={Understanding the difficulty of training deep feedforward neural networks},
  author={Glorot, Xavier and Bengio, Yoshua},
  booktitle={Proceedings of the thirteenth international conference on artificial intelligence and statistics},
  pages={249--256},
  year={2010}
}

@article{DBLP:journals/corr/ShrivastavaPTSW16,
  author    = {Ashish Shrivastava and
               Tomas Pfister and
               Oncel Tuzel and
               Josh Susskind and
               Wenda Wang and
               Russell Webb},
  title={Learning from Simulated and Unsupervised Images through Adversarial Training},
  journal={CoRR},
  volume={abs/1612.07828},
  year={2016},
  url={http://arxiv.org/abs/1612.07828}
}

@book{Goodfellow-et-al-2016,
  title={Deep Learning},
  author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
  publisher={MIT Press},
  note={\url{http://www.deeplearningbook.org}},
  year={2016}
}

@book{early_stopping, 
  author={Prechelt L.},
  year={1998}, 
  title={Early Stopping - But When?} ,
  booktitle={Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science}, 
  volume={1524},
  publisher={Springer, Berlin, Heidelberg}
}

@article{DBLP:journals/corr/IoffeS15,
  author    = {Sergey Ioffe and
               Christian Szegedy},
  title     = {Batch Normalization: Accelerating Deep Network Training by Reducing
               Internal Covariate Shift},
  journal   = {CoRR},
  volume    = {abs/1502.03167},
  year      = {2015},
  url       = {http://arxiv.org/abs/1502.03167},
  archivePrefix = {arXiv},
  eprint    = {1502.03167},
  timestamp = {Mon, 13 Aug 2018 16:47:06 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/IoffeS15},
}

@article{zhao2016energy,
  title={Energy-based generative adversarial network},
  author={Zhao, Junbo and Mathieu, Michael and LeCun, Yann},
  journal={arXiv preprint arXiv:1609.03126},
  year={2016}
}

@incollection{nguyen1990truck,
  title={The truck backer-upper: An example of self-learning in neural networks},
  author={Nguyen, Derrick and Widrow, Bernard},
  booktitle={Advanced neural computers},
  pages={11--19},
  year={1990},
  publisher={Elsevier}
}
@article{kavukcuoglu2010fast,
  title={Fast inference in sparse coding algorithms with applications to object recognition},
  author={Kavukcuoglu, Koray and Ranzato, Marc'Aurelio and LeCun, Yann},
  journal={arXiv preprint arXiv:1010.3467},
  year={2010}
}
@article{olshausen1997sparse,
  title={Sparse coding with an overcomplete basis set: A strategy employed by V1?},
  author={Olshausen, Bruno A and Field, David J},
  journal={Vision research},
  volume={37},
  number={23},
  pages={3311--3325},
  year={1997},
  publisher={Elsevier}
}
@inproceedings{gregor2010learning,
  title={Learning fast approximations of sparse coding},
  author={Gregor, Karol and LeCun, Yann},
  booktitle={Proceedings of the 27th International Conference on International Conference on Machine Learning},
  pages={399--406},
  year={2010},
  organization={Omnipress}
}
@inproceedings{denton2014exploiting,
  title={Exploiting linear structure within convolutional networks for efficient evaluation},
  author={Denton, Emily L and Zaremba, Wojciech and Bruna, Joan and LeCun, Yann and Fergus, Rob},
  booktitle={Advances in neural information processing systems},
  pages={1269--1277},
  year={2014}
}
@inproceedings{lecun1990optimal,
  title={Optimal brain damage},
  author={LeCun, Yann and Denker, John S and Solla, Sara A},
  booktitle={Advances in neural information processing systems},
  pages={598--605},
  year={1990}
}
@article{lecun1998gradient,
  title={Gradient-based learning applied to document recognition},
  author={LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick and others},
  journal={Proceedings of the IEEE},
  volume={86},
  number={11},
  pages={2278--2324},
  year={1998},
  publisher={Taipei, Taiwan}
}
@article{han2015deep,
  title={Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding},
  author={Han, Song and Mao, Huizi and Dally, William J},
  journal={arXiv preprint arXiv:1510.00149},
  year={2015}
}
@article{iandola2016squeezenet,
  title={SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size},
  author={Iandola, Forrest N and Han, Song and Moskewicz, Matthew W and Ashraf, Khalid and Dally, William J and Keutzer, Kurt},
  journal={arXiv preprint arXiv:1602.07360},
  year={2016}
}