diff --git a/mlsys.bib b/mlsys.bib index c2d3d7f..ea0a898 100644 --- a/mlsys.bib +++ b/mlsys.bib @@ -102,1756 +102,6 @@ year={2011} } - -@inproceedings{vaswani2017attention, - title={Attention is all you need}, - author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia}, - booktitle={Advances in Neural Information Processing Systems}, - pages={5998--6008}, - year={2017} -} - -@article{attentionTS, - title={Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer}, - author={Zagoruyko, Sergey and Komodakis, Nikos}, - journal={arXiv preprint arXiv:1612.03928}, - year={2016} -} - -@inproceedings{bagherinezhad2017lcnn, - title={Lcnn: Lookup-based convolutional neural network}, - author={Bagherinezhad, Hessam and Rastegari, Mohammad and Farhadi, Ali}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, - pages={7120--7129}, - year={2017} -} - -@article{Distill, - title={Distilling the knowledge in a neural network}, - author={Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff}, - journal={arXiv preprint arXiv:1503.02531}, - year={2015} -} -@article{FitNet, - title={Fitnets: Hints for thin deep nets}, - author={Romero, Adriana and Ballas, Nicolas and Kahou, Samira Ebrahimi and Chassang, Antoine and Gatta, Carlo and Bengio, Yoshua}, - journal={arXiv preprint arXiv:1412.6550}, - year={2014} -} - -@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} -} - -%% ML history -@article{hornik1989multilayer, - title={Multilayer feedforward networks are universal approximators}, - author={Hornik, Kurt and Stinchcombe, Maxwell and White, Halbert}, - journal={Neural networks}, - volume={2}, - number={5}, - pages={359--366}, - year={1989}, - publisher={Elsevier} -} - -@inproceedings{samuel1959ml, - title={Some Studies in Machine Learning Using the Game of Checkers}, - author={Samuel, Arthur}, - booktitle={IBM Journal of Research and Development}, - year={1959} -} - -@article{mcculloch1943logical, - title={A logical calculus of the ideas immanent in nervous activity}, - author={McCulloch, Warren S and Pitts, Walter}, - journal={The bulletin of mathematical biophysics}, - volume={5}, - number={4}, - pages={115--133}, - year={1943}, - publisher={Springer} -} - -@inproceedings{mai2020kungfu, - title={Kungfu: Making training in distributed machine learning adaptive}, - author={Mai, Luo and Li, Guo and Wagenl{\"a}nder, Marcel and Fertakis, Konstantinos and Brabete, Andrei-Octavian and Pietzuch, Peter}, - booktitle={14th $\{$USENIX$\}$ Symposium on Operating Systems Design and Implementation ($\{$OSDI$\}$ 20)}, - pages={937--954}, - year={2020} -} - -%%% DL Basic -@inproceedings{zhang2015textnips, - title={Character-level convolutional networks for text classification}, - author={Zhang, Xiang and Zhao, Junbo and LeCun, Yann}, - booktitle={Advances in Neural Information Processing Systems}, - pages={649--657}, - year={2015} -} - -@inproceedings{devlin-etal-2019-bert, - title = "{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding", - author = "Devlin, Jacob and - Chang, Ming-Wei and - Lee, Kenton and - Toutanova, Kristina", - booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)", - month = jun, - year = "2019", - address = "Minneapolis, Minnesota", - publisher = "Association for Computational Linguistics", - url = "https://www.aclweb.org/anthology/N19-1423", - doi = "10.18653/v1/N19-1423", - pages = "4171--4186", - abstract = "We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a; Radford et al., 2018), BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5 (7.7 point absolute improvement), MultiNLI accuracy to 86.7{\%} (4.6{\%} absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).", -} - -@inproceedings{yang2019xlnet, - title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding}, - author = {Yang, Zhilin and Dai, Zihang and Yang, Yiming and Carbonell, Jaime and Salakhutdinov, Russ R and Le, Quoc V}, - booktitle = {Advances in Neural Information Processing Systems}, - pages = {5754--5764}, - year = {2019}, -} - -@article{radford2019language, - title={Language models are unsupervised multitask learners}, - author={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya}, - journal={OpenAI Blog}, - volume={1}, - number={8}, - year={2019} -} - -@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} -} - -@article{cybenko1989approximation, - title={Approximation by superpositions of a sigmoidal function}, - author={Cybenko, George}, - journal={Mathematics of control, signals and systems}, - volume={2}, - number={4}, - pages={303--314}, - year={1989}, - publisher={Springer} -} - -@article{bubeck2012regret, - title={Regret analysis of stochastic and nonstochastic multi-armed bandit problems}, - author={Bubeck, S{\'e}bastien and Cesa-Bianchi, Nicolo and others}, - journal={Foundations and Trends{\textregistered} in Machine Learning}, - volume={5}, - number={1}, - pages={1--122}, - year={2012}, - publisher={Now Publishers, Inc.} -} - -@book{bishop2006pattern, - title={Pattern recognition and machine learning}, - author={Bishop, Christopher M}, - year={2006}, - publisher={springer} -} - -% already in this bibtext -% @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} -% } - -@inproceedings{zoph2018learning, - title={Learning transferable architectures for scalable image recognition}, - author={Zoph, Barret and Vasudevan, Vijay and Shlens, Jonathon and Le, Quoc V}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, - pages={8697--8710}, - year={2018} -} - -@article{zoph2016neural, - title={Neural architecture search with reinforcement learning}, - author={Zoph, Barret and Le, Quoc V}, - journal={arXiv preprint arXiv:1611.01578}, - year={2016} -} - -@inproceedings{krizhevsky2012imagenet, - title={Imagenet classification with deep convolutional neural networks}, - author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E}, - booktitle={Advances in Neural Information Processing Systems}, - pages={1097--1105}, - year={2012} -} - -@article{lecun1989backpropagation, - title={Backpropagation applied to handwritten zip code recognition}, - author={LeCun, Yann and Boser, Bernhard and Denker, John S and Henderson, Donnie and Howard, Richard E and Hubbard, Wayne and Jackel, Lawrence D}, - journal={Neural computation}, - volume={1}, - number={4}, - pages={541--551}, - year={1989}, - publisher={MIT Press} -} - -@article{lecun2015deep, - title={Deep learning}, - author={LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey}, - journal={Nature}, - volume={521}, - number={7553}, - pages={436}, - year={2015}, - publisher={Nature Publishing Group} -} - -@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{rumelhart1986learning, - title={Learning representations by back-propagating errors}, - author={Rumelhart, David E and Hinton, Geoffrey E and Williams, Ronald J}, - journal={Nature}, - volume={323}, - number={6088}, - pages={533}, - year={1986}, - publisher={Nature Publishing Group} -} - -@misc{olah_2015, - title={Understanding LSTM Networks}, url={https://colah.github.io/posts/2015-08-Understanding-LSTMs/}, - author={Olah, Christopher}, - year={2015}, - month={Aug} -} - -@inproceedings{glorot2011relu, - title={Deep sparse rectifier neural networks}, - author={Glorot, Xavier and Bordes, Antoine and Bengio, Yoshua}, - booktitle={Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)}, - pages={315--323}, - year={2011} -} -@article{lennie2003cost, - title={The cost of cortical computation}, - author={Lennie, Peter}, - journal={Current biology}, - volume={13}, - number={6}, - pages={493--497}, - year={2003}, - publisher={Elsevier} -} - -@inproceedings{xu2015leakyrelu, - title={Empirical evaluation of rectified activations in convolutional network}, - author={Xu, Bing and Wang, Naiyan and Chen, Tianqi and Li, Mu}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML) Workshop}, - year={2015} -} -@inproceedings{he2015prelu, - title={Delving deep into rectifiers: Surpassing human-level performance on imagenet classification}, - author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, - booktitle={Proceedings of the IEEE international conference on computer vision}, - pages={1026--1034}, - year={2015} -} -@article{srivastava2014dropout, - title={Dropout: A simple way to prevent neural networks from overfitting}, - author={Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan}, - journal={Journal of Machine Learning Research (JMLR)}, - volume={15}, - number={1}, - pages={1929--1958}, - year={2014}, -} -@article{HintonDropout2012, - title={Improving neural networks by preventing co-adaptation of feature detectors}, - author={Hinton, Geoffrey E and Srivastava, Nitish and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan R}, - journal={arXiv preprint arXiv:1207.0580}, - year={2012} -} - -@inproceedings{auer1995gambling, - title={Gambling in a rigged casino: The adversarial multi-armed bandit problem}, - author={Auer, Peter and Cesa-Bianchi, Nicolo and Freund, Yoav and Schapire, Robert E}, - booktitle={Proceedings of IEEE 36th Annual Foundations of Computer Science}, - pages={322--331}, - year={1995}, - organization={IEEE} -} - -@inproceedings{gal2016dropoutbayesian, - title={Dropout as a Bayesian approximation: Representing model uncertainty in deep learning}, - author={Gal, Yarin and Ghahramani, Zoubin}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - pages={1050--1059}, - year={2016} -} -@inproceedings{hara2017dropoutensemble, - title={Analysis of dropout learning regarded as ensemble learning}, - author={Hara, Kazuyuki and Saitoh, Daisuke and Shouno, Hayaru}, - booktitle={Proceedings of the International Conference on Artificial Neural Networks (ICANN)}, - pages={72--79}, - year={2016}, - organization={Springer} -} -@inproceedings{WanDropconnect2013, - title={Regularization of neural networks using dropconnect}, - author={Wan, Li and Zeiler, Matthew and Zhang, Sixin and Le Cun, Yann and Fergus, Rob}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - pages={1058--1066}, - year={2013} -} -@article{UncertaintyPhD, - title={Uncertainty in deep learning}, - author={Gal, Yarin}, - journal={University of Cambridge}, - year={2016} -} -@article{RandomGaussianWeights, - title={Deep neural networks with random gaussian weights: A universal classification strategy?}, - author={Giryes, Raja and Sapiro, Guillermo and Bronstein, Alexander M}, - journal={IEEE Transaction of Signal Processing}, - volume={64}, - number={13}, - pages={3444--3457}, - year={2016} -} -@inproceedings{BlundellGaussianNN2015, - title={Weight uncertainty in neural networks}, - author={Blundell, Charles and Cornebise, Julien and Kavukcuoglu, Koray and Wierstra, Daan}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2015} -} -@article{goodfellow2013maxout, - title={Maxout networks}, - author={Goodfellow, Ian J and Warde-Farley, David and Mirza, Mehdi and Courville, Aaron and Bengio, Yoshua}, - journal={The Journal of Machine Learning Research (JMLR)}, - year={2013} -} - -@inproceedings{maas2011sentiment, - author = {Maas, Andrew L. and Daly, Raymond E. and Pham, Peter T. and Huang, Dan and Ng, Andrew Y. and Potts, Christopher}, - title = {Learning Word Vectors for Sentiment Analysis}, - booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1}, - series = {HLT '11}, - year = {2011}, - isbn = {978-1-932432-87-9}, - location = {Portland, Oregon}, - pages = {142--150}, - numpages = {9}, - url = {http://dl.acm.org/citation.cfm?id=2002472.2002491}, - acmid = {2002491}, - publisher = {Association for Computational Linguistics}, - address = {Stroudsburg, PA, USA}, -} - -@inproceedings{wavenet2016, -title = {{WaveNet}: A Generative Model for Raw Audio}, -author = {Aaron van den Oord and Sander Dieleman and Heiga Zen and Karen Simonyan and Oriol Vinyals and Alexander Graves and Nal Kalchbrenner and Andrew Senior and Koray Kavukcuoglu}, -year = {2016}, -URL = {https://arxiv.org/abs/1609.03499}, -booktitle = {Arxiv} -} - - - - -%%% 1. AE -@inproceedings{Baldi2012, - issn = {0899-7667}, - booktitle = {Proceedings oast the International Conference on Machine Learning (ICML)}, - pages = {37--50}, - title = {{Autoencoders, Unsupervised Learning, and Deep Architectures}}, - author={Pierre Baldi}, - year = {2012} -} - -@inproceedings{vincent2008denoisingae, - title={Extracting and composing robust features with denoising autoencoders}, - author={Vincent, Pascal and Larochelle, Hugo and Bengio, Yoshua and Manzagol, Pierre Antoine}, - booktitle={Proceedings of the international conference on Machine learning (ICML)}, - pages={1096--1103}, - year={2008}, - organization={ACM} -} -@article{vincent2010stacked, - title={Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion}, - author={Vincent, Pascal and Larochelle, Hugo and Lajoie, Isabelle and Bengio, Yoshua and Manzagol, Pierre-Antoine}, - journal={Journal of Machine Learning Research (JMLR)}, - volume={11}, - number={Dec}, - pages={3371--3408}, - year={2010} -} -%%% 2. VAE -@inproceedings{kingma2014auto, - title={Auto-encoding variational bayes}, - author={Kingma, Diederik P and Welling, Max}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2014} -} - - -%%% 3. GANs : DCGAN, ACGAN, Semi-supervised GAN, text2image, InfoGAN, stackGAN, SRGAN -% GAN -@inproceedings{goodfellow2014gan, - title={{Generative Adversarial Nets}}, - author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2014} -} -% WGAN -@inproceedings{arjovsky2017wasserstein, - title={Wasserstein generative adversarial networks}, - author={Arjovsky, Martin and Chintala, Soumith and Bottou, L{\'e}on}, - booktitle={Processing of the International Conference on Machine Learning (ICML)}, - pages={214--223}, - year={2017} -} -% cGAN -@article{mirza2014conditional, - title={{Conditional Generative Adversarial Nets}}, - author={Mirza, Mehdi and Osindero, Simon}, - journal={arXiv preprint arXiv:1411.1784}, - year={2014} -} - -% ACGAN -@inproceedings{odena2016acgan, - title={Conditional Image Synthesis With Auxiliary Classifier GANs}, - author={Odena, Augustus and Olah, Christopher and Shlens, Jonathon}, - booktitle={Processing of the International Conference on Machine Learning (ICML)}, - year={2017} -} - -% infoGAN -@inproceedings{van2016conditional, - title={{Conditional Image Generation with PixelCNN Decoders}}, - author={Oord, Aaron Van den and Kalchbrenner, Nal and Vinyals, Oriol and Espeholt, Lasse and Graves, Alex and Kavukcuoglu, Koray}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2016} -} - -% CycleGAN -@inproceedings{zhu2017cyclegan, - author = {Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A.}, - title = {{Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks}}, - booktitle={Proceedings of International Conference on Computer Vision (ICCV)}, - year = {2017} -} -% DiscoGAN == CycleGAN -@inproceedings{kim2017discogan, - title={Learning to discover cross-domain relations with generative adversarial networks}, - author={Kim, Taeksoo and Cha, Moonsu and Kim, Hyunsoo and Lee, Jungkwon and Kim, Jiwon}, - booktitle={Processing of the International Conference on Machine Learning (ICML)}, - year={2017} -} -％ DualGAN == CycleGAN -@inproceedings{yi2017dualgan, - title={Dualgan: Unsupervised dual learning for image-to-image translation}, - author={Yi, Zili and Zhang, Hao and Tan, Ping and Gong, Minglun}, - booktitle={Proceedings of the International Conference on Computer Vision (ICCV)}, - year={2017} -} -% unsup im2im Advances in Neural Information Processing Systems -@inproceedings{liu2017unsupervised, - title={Unsupervised image-to-image translation networks}, - author={Liu, Ming-Yu and Breuel, Thomas and Kautz, Jan}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - pages={700--708}, - year={2017} -} - -@inproceedings{zhu2017toward, - author = {Zhu, Jun-Yan and Zhang, Richard and Pathak, Deepak and Darrell, Trevor and Efros, Alexei A. and Wang, Oliver and Shechtman, Eli}, - title = {{Toward Multimodal Image-to-Image Translation}}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year = {2017} -} - -% LSGAN -@inproceedings{mao2017lsgan, - title={Least squares generative adversarial networks}, - author={Mao, Xudong and Li, Qing and Xie, Haoran and Lau, Raymond YK and Wang, Zhen and Smolley, Stephen Paul}, - booktitle={Proceedings of the International Conference on Computer Vision (ICCV)}, - pages={2813--2821}, - year={2017}, - organization={IEEE} -} - -% SeqGAN -@inproceedings{yu2017seqgan, - author = {Yu, Lantao and Zhang, Weinan and Wang, Jun and Yu, Yong}, - booktitle = {Association for the Advancement of Artificial Intelligence Conference (AAAI)}, - title = {{SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient}}, - url = {http://arxiv.org/abs/1609.05473}, - year = {2017} -} -% PixelRNN -@inproceedings{oord2016pixel, - title={{Pixel Recurrent Neural Networks}}, - author={Oord, Aaron Van den and Kalchbrenner, Nal and Kavukcuoglu, Koray}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2016} -} -% InfoGAN -@inproceedings{chen2016infogan, - title={{InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets}}, - author={Chen, Xi and Duan, Yan and Houthooft, Rein and Schulman, John and Sutskever, Ilya and Abbeel, Pieter}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2016} -} -% GAN speech enhancement -@inproceedings{donahue2018exploring, - title={Exploring speech enhancement with generative adversarial networks for robust speech recognition}, - author={Donahue, Chris and Li, Bo and Prabhavalkar, Rohit}, - booktitle={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, - pages={5024--5028}, - year={2018}, - organization={IEEE} -} - -@inproceedings{odena2016semi, - title={Semi-Supervised Learning with Generative Adversarial Networks}, - author={Odena, Augustus}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML) Workshop}, - year={2016} -} - -% DCGAN -@inproceedings{radford2015dcgan, - title={{Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks}}, - author={Radford, Alec and Metz, Luke and Chintala, Soumith}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2016} -} - -@inproceedings{denton2015deep, - title = {{Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks}}, - author = {Denton, Emily and Chintala, Soumith and Szlam, Arthur and Fergus, Rob}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2015} -} - -% inception score -@inproceedings{salimans2014improved, - title={{Improved Techniques for Training GANs}}, - author={Salimans, Tim and Goodfellow, Ian and Zaremba, Wojciech and Cheung, Vicki and Radford, Alec and Chen, Xi}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2016} -} -@inproceedings{heusel2017gans, - title={Gans trained by a two time-scale update rule converge to a local nash equilibrium}, - author={Heusel, Martin and Ramsauer, Hubert and Unterthiner, Thomas and Nessler, Bernhard and Hochreiter, Sepp}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2017} -} - -@article{borji2019pros, - title={Pros and cons of GAN evaluation measures}, - author={Borji, Ali}, - journal={Computer Vision and Image Understanding}, - volume={179}, - pages={41--65}, - year={2019}, - publisher={Elsevier} -} -@inproceedings{heusel2017gans, - title={Gans trained by a two time-scale update rule converge to a local nash equilibrium}, - author={Heusel, Martin and Ramsauer, Hubert and Unterthiner, Thomas and Nessler, Bernhard and Hochreiter, Sepp}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - pages={6626--6637}, - year={2017} -} - -% GAN-CLS -@inproceedings{reed2016generative, - title={{Generative Adversarial Text to Image Synthesis}}, - author={Reed, Scott and Akata, Zeynep and Yan, Xinchen and Logeswaran, Lajanugen and Schiele, Bernt and Lee, Honglak}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2016} -} - -@inproceedings{reed2016learning, - title={{Learning What and Where to Draw}}, - author={Reed, Scott and Akata, Zeynep and Mohan, Santosh and Tenka, Samuel and Schiele, Bernt and Lee, Honglak}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2016} -} -% StackGAN -@inproceedings{zhang2017stackgan, - title={{StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks}}, - author={Zhang, Han and Xu, Tao and Li, Hongsheng and Zhang, Shaoting and Huang, Xiaolei and Wang, Xiaogang and Metaxas, Dimitris}, - booktitle={Proceedings of the International Conference on Computer Vision (ICCV)}, - year={2017} -} -@article{zhang2017stackgan2, - arxivId = {1710.10916}, - author = {Zhang, Han and Xu, Tao and Li, Hongsheng and Zhang, Shaoting and Wang, Xiaogang and Huang, Xiaolei and Metaxas, Dimitris}, - title = {{StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks}}, - url = {http://arxiv.org/abs/1710.10916}, - year = {2017} -} - -% SRGAN -@inproceedings{Ledig2017photo, - title={{Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network}}, - author={Ledig, Christian and Theis, Lucas and Huszar, Ferenc and Caballero, Jose and Cunningham, Andrew and Acosta, Alejandro and Aitken, Andrew and Tejani, Alykhan and Totz, Johannes and Wang, Zehan and Shi, Wenzhe}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2017} -} -% SSIM -@article{wang2004image, - title={Image quality assessment: from error visibility to structural similarity}, - author={Wang, Zhou and Bovik, Alan C and Sheikh, Hamid R and Simoncelli, Eero P and others}, - journal={IEEE Transactions on Image Processing (TIP)}, - volume={13}, - number={4}, - pages={600--612}, - year={2004} -} -% Progressive GAN -@inproceedings{karras2017progressive, - title={Progressive growing of GANs for improved quality, stability, and variation}, - author={Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2018} -} -@inproceedings{collier2018progressively, - title={Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images}, - author={Collier, Edward and Duffy, Kate and Ganguly, Sangram and Madanguit, Geri and Kalia, Subodh and Shreekant, Gayaka and Nemani, Ramakrishna and Michaelis, Andrew and Li, Shaung and Ganguly, Auroop and others}, - booktitle={Proceedings of the International Conference on Data Mining Workshops (ICDMW)}, - pages={763--769}, - year={2018}, - organization={IEEE} -} - -@inproceedings{Yaniv2017unsupervised, - title={{Unsupervised Cross-Domain Image Generation}}, - author={Taigman, Yaniv and Polyak, Adam and Wolf, Lior}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2017} -} - -@inproceedings{zhu2016generative, - title={{Generative Visual Manipulation on the Natural Image Manifold}}, - author={Zhu, Jun-Yan and Kr{\"a}henb{\"u}hl, Philipp and Shechtman, Eli and Efros, Alexei A.}, - booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, - year={2016} -} - -@inproceedings{li2016Precomputed, - title={{Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks}}, - author={Li, Chuan and Wand, Michael}, - booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, - year={2016} -} - -@inproceedings{Yoo2016pixel, - title={{Pixel-Level Domain Transfer}}, - author={Yoo, Donggeun and Kim, Namil and Park, Sunggyun and Paek, Anthony S. and Kweon, In So}, - booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, - year={2016} -} - -@inproceedings{Brock2017neural, - title={{Neural Photo Editing with Introspective Adversarial Networks}}, - author={Brock, Andrew and Lim, Theodore and Ritchie, J. M. and Weston, Nick}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2017} -} - -@inproceedings{wang2016generative, - title={{Generative Image Modeling Using Style and Structure Adversarial Networks}}, - author={Wang, Xiaolong and Gupta, Abhinav}, - booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, - year={2016} -} - -@inproceedings{perarnau2016icgan, - title={{Invertible Conditional GANs for Image Editing}}, - author={Perarnau, Guim and Weijer, Joost Van De and Raducanu, Bogdan and {\'{A}}lvarez, Jose M and Csiro, Data}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Workshop}, - year={2016} -} - -% BiGAN -@inproceedings{dumoulin2016adversarially, - title={{Adversarially Learned Inference}}, - author={Dumoulin, Vincent and Belghazi, Ishmael and Poole, Ben and Lamb, Alex and Arjovsky, Martin and Mastropietro, Olivier and Courville, Aaron}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2017} -} - -@inproceedings{donahue2016adversarial, - title={{Adversarial Feature Learning}}, - author={Donahue, Jeff and Kr{\"a}henb{\"u}hl, Philipp and Darrell, Trevor}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2017} -} - -% AAE -@inproceedings{makhzani2016aae, - title={{Adversarial Autoencoders}}, - author={Makhzani, Alireza and Shlens, Jonathon and Jaitly, Navdeep and Goodfellow, Ian and Frey, Brendan}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2016} -} - -% VAE+GAN VAE/GAN -@inproceedings{larsen2016vaegan, - title={{Autoencoding Beyond Pixels Using a Learned Similarity Metric}}, - author={Larsen, Anders Boesen Lindbo and S{\o}nderby, S{\o}ren Kaae and Larochelle, Hugo and Winther, Ole}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2016} -} -% GAN collapse ICCV talk -- AlphaGAN -@misc{rosca2017talk, - title = {Solving mode collapse with Autoencoder GAN}, - author = {Rosca, Mihaela and Lakshminarayanan, Balaji and Warde-Farley, David and Mohamed, Shakir}, - url = {{http://elarosca.net/slides/iccv\_autoencoder\_gans.pdf}}, -} -@article{rosca2017alphagan, - title={Variational approaches for auto-encoding generative adversarial networks}, - author={Rosca, Mihaela and Lakshminarayanan, Balaji and Warde-Farley, David and Mohamed, Shakir}, - journal={arXiv preprint arXiv:1706.04987}, - year={2017} -} -% noisy label GAN -@misc{ganhacks, - title = {How to Train a GAN? Tips and tricks to make GANs work}, - author = {Chintala, Soumith and Denton, Emily and Arjovsky, Martin and Mathieu, Michael}, - url = {{https://github.com/soumith/ganhacks}}, -} -@inproceedings{Salimans2016, - author = {Salimans, Tim and Goodfellow, Ian and Zaremba, Wojciech and Cheung, Vicki and Radford, Alec and Chen, Xi}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - title = {{Improved Techniques for Training GANs}}, - year = {2016} -} - -% unrolled GAN -@inproceedings{metz2016unrolled, - title={Unrolled generative adversarial networks}, - author={Metz, Luke and Poole, Ben and Pfau, David and Sohl-Dickstein, Jascha}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2017} -} -%@misc{kvfrans2016, -% title = {Generative Adversarial Networks Explained}, -% author = {Frans, Kevin}, -% url = {{http://kvfrans.com/generative-adversial-networks-explained/}}, -%} - - -% AGE -@inproceedings{ulyanov2018age, - title={It Takes (Only) Two: Adversarial Generator-Encoder Networks}, - author={Ulyanov, Dmitry and Vedaldi, Andrea and Lempitsky, Victor}, - booktitle={Association for the Advancement of Artificial Intelligence Conference (AAAI)}, - year={2018} -} -% other VAE/GAN -@article{mescheder2017adversarial, - title={Adversarial variational bayes: Unifying variational autoencoders and generative adversarial networks}, - author={Mescheder, Lars and Nowozin, Sebastian and Geiger, Andreas}, - journal={arXiv preprint arXiv:1701.04722}, - year={2017} -} - -% residual net resnet -@inproceedings{he2016deep, - title={{Deep Residual Learning for Image Recognition}}, - author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2016} -} - -@inproceedings{gurumurthy2017deligan, - title={{DeliGAN: Generative adversarial networks for diverse and limited data}}, - author={Gurumurthy, Swaminathan and Sarvadevabhatla, Ravi Kiran and Radhakrishnan, V Babu}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - volume={1}, - year={2017} -} - -% Style Transfer and Super Resolution -@inproceedings{johnson2016perceptual, - title={{Perceptual Losses for Real-Time Style Transfer and Super-Resolution}}, - author={Johnson, Justin and Alahi, Alexandre and Fei-Fei, Li}, - booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, - year={2016}, -} - -@book{Nasrollahi2014, - author = {Nasrollahi, Kamal and Moeslund, Thomas B.}, - booktitle = {Machine Vision and Applications}, - doi = {10.1007/s00138-014-0623-4}, - eprint = {1610.04490}, - pages = {1423--1468}, - title = {{Super-resolution: A comprehensive survey}}, - volume = {25}, - year = {2014} -} - -@article{Zou2012, - author = {Zou, Wilman}, - journal = {IEEE Transactions on Image Processing (TIP}, - number = {3}, - pages = {4408--4410}, - title = {{Very Low Resolution Face Recognition in Parallel Environment}}, - volume = {3}, - year = {2012} -} - -@inproceedings{Yang2007, - author = {Yang, Qingxiong and Yang, Ruigang and Davis, James and Nist�r, David}, - doi = {10.1109/CVPR.2007.383211}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - title = {{Spatial-Depth Supre Resolution for Range Images}}, - year = {2007} -} - -@inproceedings{Lotter2016, - author = {Lotter, William and Kreiman, Gabriel and Cox, David}, - booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)}, - number = {2015}, - pages = {1--12}, - title = {{Unsupervised Learning of Visual Structure using Predictive Generative Networks}}, - year = {2016} -} - -%% 4. Other Generative Papers -@article{oord2016pixelcnn, - title={Conditional image generation with PixelCNN decoders}, - author={Oord, Aaron van den and Kalchbrenner, Nal and Vinyals, Oriol and Espeholt, Lasse and Graves, Alex and Kavukcuoglu, Koray}, - journal={arXiv preprint arXiv:1606.05328}, - year={2016} -} - -@inproceedings{nguyen2016plug, - title={Plug \& Play Generative Networks: Conditional Iterative Generation of Images in Latent Space}, - author={Nguyen, Anh and Yosinski, Jason and Bengio, Yoshua and Dosovitskiy, Alexey and Clune, Jeff}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2017} -} - -@inproceedings{van2016conditional, - title={{Conditional Image Generation with PixelCNN Decoders}}, - author={Oord, Aaron Van den and Kalchbrenner, Nal and Vinyals, Oriol and Espeholt, Lasse and Graves, Alex and Kavukcuoglu, Koray}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2016} -} - -@inproceedings{oord2016pixel, - title={{Pixel Recurrent Neural Networks}}, - author={Oord, Aaron Van den and Kalchbrenner, Nal and Kavukcuoglu, Koray}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2016} -} - -@inproceedings{reed2016controlgenerate, - title={GENERATING INTERPRETABLE IMAGES WITH CONTROLLABLE STRUCTURE}, - author={Reed, Scott and van den Oord, A and Kalchbrenner, N and Bapst, V and Botvinick, M and de Freitas, N}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2017} -} - -@inproceedings{reed2016whatwhere, - title={Learning what and where to draw}, - author={Reed, Scott and Akata, Zeynep and Mohan, Santosh and Tenka, Samuel and Schiele, Bernt and Lee, Honglak}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2016} -} - -@inproceedings{gregor2014draw, - author = {Gregor, Karol and Danihelka, Ivo and Graves, Alex and Wierstra, Daan}, - title = {{DRAW: A Recurrent Neural Network For Image Generation}}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year = {2015} -} - - -%% 5. Image Captioning -@article{vinyals2016show, - title={Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge}, - author={Vinyals, Oriol and Toshev, Alexander and Bengio, Samy and Erhan, Dumitru}, - year={2016}, - journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)} -} -@inproceedings{xu2015show, - title={Show, attend and tell: Neural image caption generation with visual attention}, - author={Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron and Salakhudinov, Ruslan and Zemel, Rich and Bengio, Yoshua}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - pages={2048--2057}, - year={2015} -} -@misc{tensorflowmodel_im2txt, - title = {TensorFlow models : Show and Tell: A Neural Image Caption Generator}, - author = {Chris, Shallue}, - url = {{https://github.com/tensorflow/models/tree/master/research/im2txt}}, -} - -@inproceedings{karpathy2015deep, - title={Deep visual-semantic alignments for generating image descriptions}, - author={Karpathy, Andrej and Fei-Fei, Li}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2015} -} - -@inproceedings{antol2016vqa, - author = {Antol, Stanislaw and Agrawal, Aishwarya and Lu, Jiasen and Mitchell, Margaret and Batra, Dhruv and Zitnick, C. Lawrence and Parikh, Devi}, - doi = {10.1109/ICCV.2015.279}, - booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, - pages = {2425--2433}, - title = {{VQA: Visual question answering}}, - volume = {11-18-Dece}, - year = {2016} -} - -@inproceedings{kulkarni2011baby, - title={Baby talk: Understanding and generating image descriptions}, - author={Kulkarni, Girish and Premraj, Visruth and Dhar, Sagnik and Li, Siming and Choi, Yejin and Berg, Alexander C and Berg, Tamara L}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2011}, - organization={Citeseer} -} -@inproceedings{farhadi2010every, - title={Every picture tells a story: Generating sentences from images}, - author={Farhadi, Ali and Hejrati, Mohsen and Sadeghi, Mohammad Amin and Young, Peter and Rashtchian, Cyrus and Hockenmaier, Julia and Forsyth, David}, - booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, - pages={15--29}, - year={2010}, - organization={Springer} -} -%% 6. Text-image mapping and Word embedding -@article{kiros2015unifying, - title={Unifying visual-semantic embeddings with multimodal neural language models}, - author={Kiros, Ryan and Salakhutdinov, Ruslan and Zemel, Richard S}, - journal={Transactions of the Association for Computational Linguistics (TACL)}, - year={2015} -} - -@inproceedings{karpathy2014txtimmap, - title={Deep fragment embeddings for bidirectional image sentence mapping}, - author={Karpathy, Andrej and Joulin, Armand and Li, Fei Fei F}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2014} -} - -@inproceedings{mikolov2013distributed, - title={Distributed representations of words and phrases and their compositionality}, - author={Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg S and Dean, Jeff}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - pages={3111--3119}, - year={2013} -} - -@inproceedings{reed2016learningdeep, - title={{Learning Deep Representations of Fine-Grained Visual Descriptions}}, - author={Reed, Scott and Akata, Zeynep and Lee, Honglak and Schiele, Bernt}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2016} -} - -@article{rong2014word2vec, - title={Word2vec parameter learning explained}, - author={Rong, Xin}, - journal={arXiv preprint arXiv:1411.2738}, - year={2014} -} -% word2vec original paper -@article{mikolov2013efficient, - title={Efficient estimation of word representations in vector space}, - author={Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey}, - journal={Computing Research Repository (CoRR)}, - year={2013} -} -@inproceedings{pennington2014glove, - title={Glove: Global vectors for word representation}, - author={Pennington, Jeffrey and Socher, Richard and Manning, Christopher}, - booktitle={Proceedings of the Empirical Methods in Natural Language Processing (EMNLP) Conference}, - pages={1532--1543}, - year={2014} -} -@article{zhang2010understanding, - title={Understanding bag-of-words model: a statistical framework}, - author={Zhang, Yin and Jin, Rong and Zhou, Zhi-Hua}, - journal={International Journal of Machine Learning and Cybernetics}, - volume={1}, - number={1-4}, - pages={43--52}, - year={2010}, - publisher={Springer} -} -%% 7. CNN architecture sub-pixel resize convolution -@inproceedings{szegedy2015inception, - title={Rethinking the inception architecture for computer vision}, - author={Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jonathon and Wojna, Zbigniew}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2016} -} - -@article{odena2016resizeconv, - title={Rethinking the inception architecture for computer vision}, - author={Odena, Augustus and Vincent, Dumoulinand Chris, Olah}, - journal={Distill}, - year={2016} -} - - -%% 8. CNN unsupervised for 3D structure -@article{rezende2016unsupervised, - title={Unsupervised learning of 3d structure from images}, - author={Rezende, Danilo Jimenez and Eslami, SM and Mohamed, Shakir and Battaglia, Peter and Jaderberg, Max and Heess, Nicolas}, - journal={arXiv preprint arXiv:1607.00662}, - year={2016} -} - -%% 9. Traditional Im2im -@article{bitouk2008face, - title={Face swapping: automatically replacing faces in photographs}, - author={Bitouk, Dmitri and Kumar, Neeraj and Dhillon, Samreen and Belhumeur, Peter and Nayar, Shree K}, - journal={ACM Transactions on Graphics (TOG)}, - volume={27}, - number={3}, - pages={39}, - year={2008}, - publisher={ACM} -} - -@article{korshunova2016fast, - title={Fast Face-swap Using Convolutional Neural Networks}, - author={Korshunova, Iryna and Shi, Wenzhe and Dambre, Joni and Theis, Lucas}, - journal={arXiv preprint arXiv:1611.09577}, - year={2016} -} - -@article{chen2009sketch2photo, - title={Sketch2Photo: internet image montage}, - author={Chen, Tao and Cheng, Ming-Ming and Tan, Ping and Shamir, Ariel and Hu, Shi-Min}, - journal={ACM Transactions on Graphics (TOG)}, - volume={28}, - number={5}, - pages={124}, - year={2009}, - publisher={ACM} -} - -@article{shih2013data, - title={Data-driven hallucination of different times of day from a single outdoor photo}, - author={Shih, Yichang and Paris, Sylvain and Durand, Fr{\'e}do and Freeman, William T}, - journal={ACM Transactions on Graphics (TOG)}, - volume={32}, - number={6}, - pages={200}, - year={2013}, - publisher={ACM} -} - -@article{laffont2014transient, - title={Transient attributes for high-level understanding and editing of outdoor scenes}, - author={Laffont, Pierre-Yves and Ren, Zhile and Tao, Xiaofeng and Qian, Chao and Hays, James}, - journal={ACM Transactions on Graphics (TOG)}, - volume={33}, - number={4}, - pages={149}, - year={2014}, - publisher={ACM} -} - -@inproceedings{taigman2016unsupervised, - title={Unsupervised Cross-Domain Image Generation}, - author={Taigman, Yaniv and Polyak, Adam and Wolf, Lior}, - booktitle={Proceedings of the International Conference on Learning Representations (ICLR)}, - year={2017} -} - -@article{Hochreiter1997lstm, - author = {Hochreiter, Sepp and Hochreiter, S and Schmidhuber, J{\"{u}}rgen and Schmidhuber, J}, - isbn = {08997667 (ISSN)}, - issn = {0899-7667}, - journal = {Neural Computation}, - number = {8}, - pages = {1735--80}, - pmid = {9377276}, - title = {{Long Short-Term Memory.}}, - volume = {9}, - year = {1997} -} - -@article{greff2017lstm, - title={{LSTM}: A search space odyssey}, - author={Greff, Klaus and Srivastava, Rupesh K and Koutn{\'\i}k, Jan and Steunebrink, Bas R and Schmidhuber, J{\"u}rgen}, - journal={IEEE Transactions on Neural Networks and Learning Systems (TNNLS)}, - volume={28}, - number={10}, - pages={2222--2232}, - year={2017}, - publisher={IEEE} -} - -%%% -@inproceedings{girshick2015fastrcnn, - title={{Fast R-CNN}}, - author={Girshick, Ross}, - booktitle={Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, - pages={1440--1448}, - year={2015} -} - -%% domain adaptation -@inproceedings{zhao2018adversarial, - title={Adversarial multiple source domain adaptation}, - author={Zhao, Han and Zhang, Shanghang and Wu, Guanhang and Moura, Jos{\'e} MF and Costeira, Joao P and Gordon, Geoffrey J}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - pages={8568--8579}, - year={2018} -} - -%%% Seq2Seq language translation GRU -@inproceedings{cho2014learning, - title={Learning phrase representations using {RNN} encoder-decoder for statistical machine translation}, - author={Cho, Kyunghyun and Van Merri{\"e}nboer, Bart and Gulcehre, Caglar and Bahdanau, Dzmitry and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua}, - booktitle={Proceedings of the Empirical Methods in Natural Language Processing (EMNLP) Conference}, - year={2014} -} - -@inproceedings{jozefowicz2015empirical, - title={An empirical exploration of recurrent network architectures}, - author={Jozefowicz, Rafal and Zaremba, Wojciech and Sutskever, Ilya}, - booktitle={International Conference on Machine Learning}, - pages={2342--2350}, - year={2015} -} - -@inproceedings{sutskever2014sequence, - title={Sequence to sequence learning with neural networks}, - author={Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - pages={3104--3112}, - year={2014} -} - -@inproceedings{rezende2014stochastic, - title={{Stochastic Backpropagation and Approximate Inference in Deep Generative Models}}, - author={Rezende, Danilo Jimenez and Mohamed, Shakir and Wierstra, Daan}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2014} -} - -@inproceedings{liao2018deep, - title={Deep sequence learning with auxiliary information for traffic prediction}, - author={Liao, Binbing and Zhang, Jingqing and Wu, Chao and McIlwraith, Douglas and Chen, Tong and Yang, Shengwen and Guo, Yike and Wu, Fei}, - booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining}, - pages={537--546}, - year={2018}, - organization={ACM} -} - -@inproceedings{liao2018dest, - title={{Dest-ResNet}: A Deep Spatiotemporal Residual Network for Hotspot Traffic Speed Prediction}, - author={Liao, Binbing and Zhang, Jingqing and Cai, Ming and Tang, Siliang and Gao, Yifan and Wu, Chao and Yang, Shengwen and Zhu, Wenwu and Guo, Yike and Wu, Fei}, - booktitle={2018 ACM Multimedia Conference on Multimedia Conference}, - pages={1883--1891}, - year={2018}, - organization={ACM} -} - -@article{song2019arena, - title={Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence}, - author={Song, Yuhang and Wang, Jianyi and Lukasiewicz, Thomas and Xu, Zhenghua and Xu, Mai and Ding, Zihan and Wu, Lianlong}, - journal={arXiv preprint arXiv:1905.08085}, - year={2019} -} - - -@inproceedings{ -peterliu2018generating, -title={Generating Wikipedia by Summarizing Long Sequences}, -author={Peter J. Liu and Mohammad Saleh and Etienne Pot and Ben Goodrich and Ryan Sepassi and Lukasz Kaiser and Noam Shazeer}, -booktitle={International Conference on Learning Representations}, -year={2018}, -url={https://openreview.net/forum?id=Hyg0vbWC-}, -} - -@article{zhang2019pegasus, - title={{PEGASUS}: Pre-training with Extracted Gap-sentences for Abstractive Summarization}, - author={Zhang, Jingqing and Zhao, Yao and Saleh, Mohammad and Liu, Peter J}, - journal={arXiv preprint arXiv:1912.08777}, - year={2019} -} - - -%%% generative model vs discriminative model -@inproceedings{ng2002discriminative, - title={On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes}, - author={Ng, Andrew Y and Jordan, Michael I}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - pages={841--848}, - year={2002} -} - -@inproceedings{rish2001empirical, - title={An empirical study of the naive Bayes classifier}, - author={Rish, Irina and others}, - booktitle={International Joint Conference on Artificial Intelligence 2001 workshop on empirical methods in artificial intelligence}, - volume={3}, - number={22}, - pages={41--46}, - year={2001} -} - -%%% Computer Vision Tasks CV -@inproceedings{redmon2017yolo9000, - title={YOLO9000: better, faster, stronger}, - author={Redmon, Joseph and Farhadi, Ali}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2017} -} - -@inproceedings{long2015fully, - title={Fully convolutional networks for semantic segmentation}, - author={Long, Jonathan and Shelhamer, Evan and Darrell, Trevor}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - pages={3431--3440}, - year={2015} -} - -@inproceedings{noh2015learning, - title={Learning deconvolution network for semantic segmentation}, - author={Noh, Hyeonwoo and Hong, Seunghoon and Han, Bohyung}, - booktitle={Proceedings of the International Conference on Computer Vision (ICCV)}, - pages={1520--1528}, - year={2015} -} - -@inproceedings{cao2017realtime, - author = {Cao, Zhe and Simon, Zhe and Wei, Shih-En and Sheikh, Shih-En}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - title = {Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields}, - year = {2017} -} - -@inproceedings{he2017mask, - title={Mask R-CNN}, - author={He, Kaiming and Gkioxari, Georgia and Doll{\'a}r, Piotr and Girshick, Ross}, - booktitle={Proceedings of the International Conference on Computer Vision (ICCV)}, - pages={2980--2988}, - year={2017}, - organization={IEEE} -} - -@inproceedings{korshunova2017fast, - title={Fast face-swap using convolutional neural networks}, - author={Korshunova, Iryna and Shi, Wenzhe and Dambre, Joni and Theis, Lucas}, - booktitle={Proceedings of the International Conference on Computer Vision (ICCV)}, - year={2017} -} - -@inproceedings{xie2012image, - title={Image denoising and inpainting with deep neural networks}, - author={Xie, Junyuan and Xu, Linli and Chen, Enhong}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems}, - pages={341--349}, - year={2012} -} - -@inproceedings{liu2015deep, - title={Deep convolutional neural fields for depth estimation from a single image}, - author={Liu, Fayao and Shen, Chunhua and Lin, Guosheng}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - pages={5162--5170}, - year={2015} -} - -@article{shih2013data, - title={Data-driven hallucination of different times of day from a single outdoor photo}, - author={Shih, Yichang and Paris, Sylvain and Durand, Fr{\'e}do and Freeman, William T}, - journal={ACM Transactions on Graphics (TOG)}, - volume={32}, - number={6}, - pages={200}, - year={2013}, - publisher={ACM} -} - -@article{laffont2014transient, - title={Transient attributes for high-level understanding and editing of outdoor scenes}, - author={Laffont, Pierre-Yves and Ren, Zhile and Tao, Xiaofeng and Qian, Chao and Hays, James}, - journal={ACM Transactions on Graphics (TOG)}, - volume={33}, - number={4}, - pages={149}, - year={2014}, - publisher={ACM} -} - -@article{chen2009sketch2photo, - title={Sketch2photo: Internet image montage}, - author={Chen, Tao and Cheng, Ming-Ming and Tan, Ping and Shamir, Ariel and Hu, Shi-Min}, - journal={ACM Transactions on Graphics (TOG)}, - volume={28}, - number={5}, - pages={124}, - year={2009}, - organization={ACM} -} - -%%% understand CNN - -@article{mahendran2016visualizing, - title={Visualizing deep convolutional neural networks using natural pre-images}, - author={Mahendran, Aravindh and Vedaldi, Andrea}, - journal={International Journal of Computer Vision (IJCV)}, - volume={120}, - number={3}, - pages={233--255}, - year={2016}, - publisher={Springer} -} - -@article{dumoulin2016guide, - title={A guide to convolution arithmetic for deep learning}, - author={Dumoulin, Vincent and Visin, Francesco}, - journal={arXiv preprint arXiv:1603.07285}, - year={2016} -} - -@article{yin2017comparative, - title={Comparative study of CNN and RNN for natural language processing}, - author={Yin, Wenpeng and Kann, Katharina and Yu, Mo and Sch{\"u}tze, Hinrich}, - journal={arXiv preprint arXiv:1702.01923}, - year={2017} -} - - - -%%% understand rnn - -@article{chung2014empirical, - title={Empirical evaluation of gated recurrent neural networks on sequence modeling}, - author={Chung, Junyoung and Gulcehre, Caglar and Cho, KyungHyun and Bengio, Yoshua}, - journal={arXiv preprint arXiv:1412.3555}, - year={2014} -} - -@inproceedings{luong-etal-2015-effective, - title = "Effective Approaches to Attention-based Neural Machine Translation", - author = "Luong, Thang and - Pham, Hieu and - Manning, Christopher D.", - booktitle = "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing", - month = sep, - year = "2015", - address = "Lisbon, Portugal", - publisher = "Association for Computational Linguistics", - url = "https://www.aclweb.org/anthology/D15-1166", - doi = "10.18653/v1/D15-1166", - pages = "1412--1421", -} - -@inproceedings{nallapati2017summarunner, - author = {Nallapati, Ramesh and Zhai, Feifei and Zhou, Bowen}, - title = {SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents}, - year = {2017}, - publisher = {AAAI Press}, - booktitle = {Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence}, - pages = {3075–3081}, - numpages = {7}, - location = {San Francisco, California, USA}, - series = {AAAI’17} -} - -@inproceedings{zhang-etal-2019-integrating, - title = "Integrating Semantic Knowledge to Tackle Zero-shot Text Classification", - author = "Zhang, Jingqing and - Lertvittayakumjorn, Piyawat and - Guo, Yike", - booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)", - month = jun, - year = "2019", - address = "Minneapolis, Minnesota", - publisher = "Association for Computational Linguistics", - url = "https://www.aclweb.org/anthology/N19-1108", - doi = "10.18653/v1/N19-1108", - pages = "1031--1040", - abstract = "Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen in the learning stage, so-called zero-shot text classification, is therefore difficult and only limited previous works tackled this problem. In this paper, we propose a two-phase framework together with data augmentation and feature augmentation to solve this problem. Four kinds of semantic knowledge (word embeddings, class descriptions, class hierarchy, and a general knowledge graph) are incorporated into the proposed framework to deal with instances of unseen classes effectively. Experimental results show that each and the combination of the two phases achieve the best overall accuracy compared with baselines and recent approaches in classifying real-world texts under the zero-shot scenario.", -} - -@inproceedings{lee-dernoncourt-2016-sequential, - title = "Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks", - author = "Lee, Ji Young and - Dernoncourt, Franck", - booktitle = "Proceedings of the 2016 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies", - month = jun, - year = "2016", - address = "San Diego, California", - publisher = "Association for Computational Linguistics", - url = "https://www.aclweb.org/anthology/N16-1062", - doi = "10.18653/v1/N16-1062", - pages = "515--520", -} - -@article{wierstra2010recurrent, - title={Recurrent policy gradients}, - author={Wierstra, Daan and F{\"o}rster, Alexander and Peters, Jan and Schmidhuber, J{\"u}rgen}, - journal={Logic Journal of the IGPL}, - volume={18}, - number={5}, - pages={620--634}, - year={2010}, - publisher={Oxford University Press} -} - - -%%% Transfer learning -@inproceedings{pratt1993discriminability, - title={Discriminability-based transfer between neural networks}, - author={Pratt, Lorien Y}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - pages={204--211}, - year={1993} -} -@article{west2007spring, - title={Spring research presentation: A theoretical foundation for inductive transfer}, - author={West, Jeremy and Ventura, Dan and Warnick, Sean}, - journal={Brigham Young University, College of Physical and Mathematical Sciences}, - volume={1}, - year={2007} -} - -%%% RL reinforcement alphago -@article{silver2017master, - title={Mastering the game of Go without human knowledge}, - author={Silver, David and Schrittwieser, Julian and Simonyan, Karen and Antonoglou, Ioannis and Huang, Aja and Guez, Arthur and Hubert, Thomas and Baker, Lucas and Lai, Matthew and Bolton, Adrian and Yutian Chen and Timothy Lillicrap and Fan Hui and Laurent Sifre and George van den Driessche and Thore Graepel and Hassabis, Demis}, - journal={Nature}, - volume={550}, - number={7676}, - pages={354}, - year={2017}, - publisher={Nature Publishing Group} -} - -@misc{pingpixel2016, - author={Andrej Karpathy}, - title = {Deep Reinforcement Learning: Pong from Pixels}, - year = {2016}, - howpublished={\url{http://karpathy.github.io/2016/05/31/rl/}}, -} - -@article{mnih2015human, - title={Human-level control through deep reinforcement learning}, - author={Volodymyr Mnih and Koray Kavukcuoglu and David Silver and Andrei A. Rusu and Joel Veness and Marc G. Bellemare and Alex Graves and Martin Riedmiller and Andreas K. Fidjeland and Georg Ostrovski and Stig Petersen and Charles Beattie and Amir Sadik and Ioannis Antonoglou and Helen King and Dharshan Kumaran and Daan Wierstra and Shane Legg and Demis Hassabis}, - journal={Nature}, - year={2015} -} - -@article{williams1992REINFORCE, - title={Simple statistical gradient-following algorithms for connectionist reinforcement learning}, - author={Williams, Ronald J}, - journal={Machine Learning}, - volume={8}, - number={3-4}, - pages={229--256}, - year={1992}, - publisher={Springer} -} - -%%% Book -@book{goodfellowDLbook2016, - title={Deep Learning}, - author={Ian Goodfellow and Yoshua Bengio and Aaron Courville}, - publisher={MIT Press}, - note={\url{http://www.deeplearningbook.org}}, - year={2016} -} -@book{affine, - title={Affine transformation}, - author={Hazewinkel, Michiel, ed.}, - publisher={Springer}, - year={2001} -} -@book{meyer1992wavelets, - title={Wavelets and applications}, - author={Meyer, Yves}, - volume={31}, - year={1992}, - publisher={Masson Paris} -} - -%% -@article{maaten2008tsne, - title={Visualizing data using t-SNE}, - author={Maaten, Laurens van der and Hinton, Geoffrey}, - journal={Journal of Machine Learning Research}, - volume={9}, - number={Nov}, - pages={2579--2605}, - year={2008} -} -%% image inpainting -@inproceedings{yeh2017inpainting, - title={Semantic image inpainting with deep generative models}, - author={Yeh, Raymond A and Chen, Chen and Yian Lim, Teck and Schwing, Alexander G and Hasegawa-Johnson, Mark and Do, Minh N}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - pages={5485--5493}, - year={2017} -} -@inproceedings{pathak2016context, - title={Context encoders: Feature learning by inpainting}, - author={Pathak, Deepak and Krahenbuhl, Philipp and Donahue, Jeff and Darrell, Trevor and Efros, Alexei A}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - pages={2536--2544}, - year={2016} -} -@inproceedings{barnes2009patchmatch, - title={PatchMatch: A randomized correspondence algorithm for structural image editing}, - author={Barnes, Connelly and Shechtman, Eli and Finkelstein, Adam and Goldman, Dan B}, - booktitle={ACM Transactions on Graphics (ToG)}, - volume={28}, - number={3}, - pages={24}, - year={2009}, - organization={ACM} -} -@article{hu2013lowrank, - title={Fast and accurate matrix completion via truncated nuclear norm regularization}, - author={Hu, Yao and Zhang, Debing and Ye, Jieping and Li, Xuelong and He, Xiaofei}, - journal={IEEE transactions on pattern analysis and machine intelligence}, - volume={35}, - number={9}, - pages={2117--2130}, - year={2013}, - publisher={IEEE} -} -%%% Datasets : MSCOCO, Imagenet, SVHN, CUB-bird, flower -@inproceedings{lin2014microsoft, - title={Microsoft COCO: Common objects in context}, - author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence}, - journal={Proceedings of the European Conference on Computer Vision (ECCV)}, - year={2014}, - organization={Springer} -} - -@inproceedings{liu2015faceattributes, - author = {Ziwei Liu and Ping Luo and Xiaogang Wang and Xiaoou Tang}, - title = {Deep Learning Face Attributes in the Wild}, - booktitle = {Proceedings of the International Conference on Computer Vision (ICCV)}, - month = December, - year = {2015} -} - -@inproceedings{netzer2011svhn, - title={Reading digits in natural images with unsupervised feature learning}, - author={Netzer, Yuval and Wang, Tao and Coates, Adam and Bissacco, Alessandro and Wu, Bo and Ng, Andrew Y}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Workshop on Deep Learning and Unsupervised Feature Learning}, - volume={2011}, - number={2}, - pages={5}, - year={2011} -} - -@techreport{WahCUB_200_2011, - Title = {{The Caltech-UCSD Birds-200-2011 Dataset}}, - Author = {Wah, C. and Branson, S. and Welinder, P. and Perona, P. and Belongie, S.}, - Year = {2011}, - Institution = {California Institute of Technology}, - Number = {CNS-TR-2011-001} -} - -@inproceedings{nilsback2008flower, - title={{Automated Flower Classification over a Large Number of Classes}}, - author={Nilsback, Maria-Elena and Zisserman, Andrew}, - booktitle={Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (ICCVGIP)}, - year={2008} -} - -@article{bellman1954theory, - title={The theory of dynamic programming}, - author={Bellman, Richard and others}, - journal={Bulletin of the American Mathematical Society}, - volume={60}, - number={6}, - pages={503--515}, - year={1954}, - publisher={American Mathematical Society} -} - -@article{russakovsky2015imagenet, - title={{Imagenet Large Scale Visual Recognition Challenge}}, - author={Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael}, - journal={International Journal of Computer Vision (IJCV)}, - volume={115}, - number={3}, - pages={211--252}, - year={2015}, - publisher={Springer} -} - -@article{krishna2017visual, - title={Visual genome: Connecting language and vision using crowdsourced dense image annotations}, - author={Krishna, Ranjay and Zhu, Yuke and Groth, Oliver and Johnson, Justin and Hata, Kenji and Kravitz, Joshua and Chen, Stephanie and Kalantidis, Yannis and Li, Li-Jia and Shamma, David A and others}, - journal={International Journal of Computer Vision}, - volume={123}, - number={1}, - pages={32--73}, - year={2017}, - publisher={Springer} -} - -%%% Dataset : IXI MICCAI - -@misc{miccaidataset, - title = {MICCAI 2013 grand challenge dataset}, - author = {}, - url = {{http://masiweb.vuse.vanderbilt.edu/workshop2013/index.php/Segmentation\_Challenge\_Details}}, -} - -@misc{ixidataset, - title = {IXI – Information eXtraction from Images}, - author = {Amir, Alansary and Paul, Aljabar and Gareth, Ball and etc}, - url = {{http://brain-development.org/ixi-dataset/}}, -} - -% MPII -@inproceedings{andriluka14cvpr, - title={2D Human Pose Estimation: New Benchmark and State of the Art Analysis}, - author={Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2014}, -} - -%% Object detection -@inproceedings{li2017perceptual, - title={Perceptual generative adversarial networks for small object detection}, - author={Li, Jianan and Liang, Xiaodan and Wei, Yunchao and Xu, Tingfa and Feng, Jiashi and Yan, Shuicheng}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - pages={1222--1230}, - year={2017} -} - -%%% Domain Adaptation -@article{ganin2016domain, - title={Domain-adversarial training of neural networks}, - author={Ganin, Yaroslav and Ustinova, Evgeniya and Ajakan, Hana and Germain, Pascal and Larochelle, Hugo and Laviolette, Fran{\c{c}}ois and Marchand, Mario and Lempitsky, Victor}, - journal={Journal of Machine Learning Research (JMLR)}, - volume={17}, - number={59}, - pages={1--35}, - year={2016} -} - -@inproceedings{chen2012marginalized, - title={Marginalized denoising autoencoders for domain adaptation}, - author={Chen, Minmin and Xu, Zhixiang and Weinberger, Kilian and Sha, Fei}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2012} -} -@inproceedings{shanghang2018multiple, - title={Multiple source domain adaptation with adversarial learning}, - author={Zhao, Han and Zhang, Shanghang and Wu, Guanhang and Gordon, Geoffrey J and others}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, year={2018} -} - -@book{hawkins2007intelligence, - title={On intelligence}, - author={Hawkins, Jeff and Blakeslee, Sandra}, - year={2007}, - publisher={Macmillan} -} - -%% -@inproceedings{dosovitskiy2015learning, - title={{Learning to Generate Chairs with Convolutional Neural Networks}}, - author={Dosovitskiy, Alexey and Tobias Springenberg, Jost and Brox, Thomas}, - booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, - year={2015} -} - -@inproceedings{yang2015weakly, - title={{Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis}}, - author={Yang, Jimei and Reed, Scott and Yang, Ming-Hsuan and Lee, Honglak}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2015} -} - -@inproceedings{reed2015deepVisual, - title={{Deep Visual Analogy-Making}}, - author={Reed, Scott and Zhang, Yi and Zhang, Yuting and Lee, Honglak}, - booktitle={Proceedings of the Neural Information Processing Systems (Advances in Neural Information Processing Systems) Conference}, - year={2015} -} - -@inproceedings{gregor2015draw, - title={Stochastic Backpropagation and Approximate Inference in Deep Generative Models}, - author={Gregor, Karol and Danihelka, Ivo and Graves, Alex and Rezende, Danilo Jimenez and Wierstra, Daan}, - booktitle={Proceedings of the International Conference on Machine Learning (ICML)}, - year={2015} -} - -@inproceedings{mansimov2016, - author = {Mansimov, Elman and Parisotto, Emilio and Ba, Jimmy Lei and Salakhutdinov, Ruslan}, - booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)}, - title = {{Generating Images from Captions with Attention}}, - year = {2016} -} - - -@inproceedings{yan2016attribute2image, - title={{Attribute2Image: Conditional Image Generation from Visual Attributes}}, - author={Yan, Xinchen and Yang, Jimei and Sohn, Kihyuk and Lee, Honglak}, - booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, - year={2016} -} -@inproceedings{niklaus2017video, - title={Video frame interpolation via adaptive separable convolution}, - author={Niklaus, Simon and Mai, Long and Liu, Feng}, - booktitle={Proceedings of the IEEE International Conference on Computer Vision}, - pages={261--270}, - year={2017} -} - -%%% Training, Optimizer, Batch Normalization -@inproceedings{KingmaAdam2014, - title = {{Adam}: A Method for Stochastic Optimization}, - author = {Kingma, Diederik and Ba, Jimmy}, - booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)}, - year = {2014} -} -@article{duchi2011adagrad, - title={Adaptive subgradient methods for online learning and stochastic optimization}, - author={Duchi, John and Hazan, Elad and Singer, Yoram}, - journal={Journal of Machine Learning Research (JMLR)}, - volume={12}, - number={Jul}, - pages={2121--2159}, - year={2011} -} - @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},