全球人工智能

文章来源：Github

对抗网络专题文献集

第一篇论文

[Generative Adversarial Nets](the first paper about it)

[Paper]：https://arxiv.org/abs/1406.2661

[Code]：https://github.com/goodfeli/adversarial

未分类

[Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks]

[Paper]https://arxiv.org/abs/1506.05751

[Code]https://github.com/facebook/eyescream

[Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](Gan with convolutional networks)(ICLR)

[Paper]https://arxiv.org/abs/1511.06434

[Code]https://github.com/jacobgil/keras-dcgan

[Adversarial Autoencoders]

[Paper]http://arxiv.org/abs/1511.05644

[Code]https://github.com/musyoku/adversarial-autoencoder

[Generating Images with Perceptual Similarity Metrics based on Deep Networks]

[Paper]https://arxiv.org/pdf/1602.02644v2.pdf

[Generating images with recurrent adversarial networks]

[Paper]https://arxiv.org/abs/1602.05110

[Code]https://github.com/ofirnachum/sequence_gan

[Generative Visual Manipulation on the Natural Image Manifold]

[Paper]https://people.eecs.berkeley.edu/%7Ejunyanz/projects/gvm/eccv16_gvm.pdf

[Code]https://github.com/junyanz/iGAN

[Generative Adversarial Text to Image Synthesis]

[Paper]https://arxiv.org/abs/1605.05396

[Code]https://github.com/reedscot/icml2016

[code]https://github.com/paarthneekhara/text-to-image

[Learning What and Where to Draw]

[Paper]http://www.scottreed.info/files/nips2016.pdf

[Code]https://github.com/reedscot/nips2016

[Adversarial Training for Sketch Retrieval]

[Paper]http://link.springer.com/chapter/10.1007/978-3-319-46604-0_55

[Generative Image Modeling using Style and Structure Adversarial Networks]

[Paper]https://arxiv.org/pdf/1603.05631.pdf

[Code]https://github.com/xiaolonw/ss-gan

[Generative Adversarial Networks as Variational Training of Energy Based Models](ICLR 2017)

[Paper]http://www.mathpubs.com/detail/1611.01799v1/Generative-Adversarial-Networks-as-Variational-Training-of-Energy-Based-Models

[Adversarial Training Methods for Semi-Supervised Text Classification]( Ian Goodfellow Paper)

[Paper]https://arxiv.org/abs/1605.07725

[Note]https://github.com/dennybritz/deeplearning-papernotes/blob/master/notes/adversarial-text-classification.md

[Learning from Simulated and Unsupervised Images through Adversarial Training]（Apple paper）

[Paper]https://arxiv.org/abs/1612.07828

[code]https://github.com/carpedm20/simulated-unsupervised-tensorflow

[Synthesizing the preferred inputs for neurons in neural networks via deep generator networks]

[Paper]https://arxiv.org/pdf/1605.09304v5.pdf

[Code]https://github.com/Evolving-AI-Lab/synthesizing

[SalGAN: Visual Saliency Prediction with Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1701.01081

[Code]https://github.com/imatge-upc/saliency-salgan-2017

[Adversarial Feature Learning]

[Paper]https://arxiv.org/abs/1605.09782

[Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks]

[Paper]https://junyanz.github.io/CycleGAN/

[Code]https://github.com/junyanz/CycleGAN

Ensemble

[AdaGAN: Boosting Generative Models] （Google Brain）

[Paper]https://arxiv.org/abs/1701.02386

聚类

[Unsupervised Learning Using Generative Adversarial Training And Clustering](ICLR)

[Paper]https://openreview.net/forum?id=SJ8BZTjeg&noteId=SJ8BZTjeg

[Code]https://github.com/VittalP/UnsupGAN

[Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks] (ICLR)

[Paper]https://arxiv.org/abs/1511.06390

Image Inpainting

[Semantic Image Inpainting with Perceptual and Contextual Losses]

[Paper]https://arxiv.org/abs/1607.07539

[Code]https://github.com/bamos/dcgan-completion.tensorflow

[Context Encoders: Feature Learning by Inpainting]

[Paper]https://arxiv.org/abs/1604.07379

[Code]https://github.com/jazzsaxmafia/Inpainting

[Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1611.06430v1

Joint Probability

[Adversarially Learned Inference]

[Paper]https://arxiv.org/abs/1606.00704

[Code]https://github.com/IshmaelBelghazi/ALI

Super-Resolution

[Image super-resolution through deep learning ](Just for face dataset)

[Code]https://github.com/david-gpu/srez

[Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network] （Using Deep residual network）

[Paper]https://arxiv.org/abs/1609.04802

[Code]https://github.com/leehomyc/Photo-Realistic-Super-Resoluton

[EnhanceGAN]

[Docs]https://medium.com/@richardherbert/faces-from-noise-super-enhancing-8x8-images-with-enhancegan-ebda015bb5e0#.io6pskvin

Disocclusion

[Robust LSTM-Autoencoders for Face De-Occlusion in the Wild]

[Paper]https://arxiv.org/abs/1612.08534

Semantic Segmentation

[Semantic Segmentation using Adversarial Networks] （soumith's paper）

[Paper]https://arxiv.org/abs/1611.08408

Object Detection

[Perceptual generative adversarial networks for small object detection]（Submitted）

[A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection](CVPR2017)

[Paper]http://abhinavsh.info/papers/pdfs/adversarial_object_detection.pdfRNN

[C-RNN-GAN: Continuous recurrent neural networks with adversarial training]

[Paper]https://arxiv.org/abs/1611.09904

[Code]https://github.com/olofmogren/c-rnn-gan

Conditional adversarial

[Conditional Generative Adversarial Nets]

[Paper]https://arxiv.org/abs/1411.1784

[Code]https://github.com/zhangqianhui/Conditional-Gans

[InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets]

[Paper]https://arxiv.org/abs/1606.03657

[Code]https://github.com/buriburisuri/supervised_infogan

[Image-to-image translation using conditional adversarial nets]

[Paper]https://arxiv.org/pdf/1611.07004v1.pdf

[Code]https://github.com/phillipi/pix2pix

[Code]https://github.com/yenchenlin/pix2pix-tensorflow

[Conditional Image Synthesis With Auxiliary Classifier GANs](GoogleBrain ICLR 2017)

[Paper]https://arxiv.org/abs/1610.09585

[Code]https://github.com/buriburisuri/ac-gan

[Pixel-Level Domain Transfer]

[Paper]https://arxiv.org/pdf/1603.07442v2.pdf

[Code]https://github.com/fxia22/pldtgan

[Invertible Conditional GANs for image editing]

[Paper]https://arxiv.org/abs/1611.06355

[Code]https://github.com/Guim3/IcGAN

[Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space]

[Paper]https://arxiv.org/abs/1612.00005v1

[Code]https://github.com/Evolving-AI-Lab/ppgn

[StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks]

[Paper]https://arxiv.org/pdf/1612.03242v1.pdf

[Code]https://github.com/hanzhanggit/StackGAN

[Unsupervised Image-to-Image Translation with Generative Adversarial Networks]

[Paper]https://arxiv.org/pdf/1701.02676.pdf

[Learning to Discover Cross-Domain Relations with Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1703.05192

[Code]https://github.com/carpedm20/DiscoGAN-pytorch

Video Prediction

[Deep multi-scale video prediction beyond mean square error] (Yann LeCun's paper)

[Paper]https://arxiv.org/abs/1511.05440

[Code]https://github.com/dyelax/Adversarial_Video_Generation

[Unsupervised Learning for Physical Interaction through Video Prediction] (Ian Goodfellow's paper)

[Paper]https://arxiv.org/abs/1605.07157

[Generating Videos with Scene Dynamics]

[Paper]https://arxiv.org/abs/1609.02612

[Web]http://web.mit.edu/vondrick/tinyvideo/

[Code]https://github.com/cvondrick/videogan

Texture Synthesis & style transfer

[Precomputed real-time texture synthesis with markovian generative adversarial networks](ECCV 2016)

[Paper]https://arxiv.org/abs/1604.04382

[Code]https://github.com/chuanli11/MGANs

GAN Theory

[Energy-based generative adversarial network](Lecun paper)

[Paper]https://arxiv.org/pdf/1609.03126v2.pdf

[Code]https://github.com/buriburisuri/ebgan

[Improved Techniques for Training GANs] (Goodfellow's paper)

[Paper]https://arxiv.org/abs/1606.03498

[Code]https://github.com/openai/improved-gan

[Mode RegularizedGenerative Adversarial Networks] (Yoshua Bengio , ICLR 2017)

[Paper]https://openreview.net/pdf?id=HJKkY35le

[Improving Generative Adversarial Networks with Denoising Feature Matching](Yoshua Bengio , ICLR 2017)

[Paper]https://openreview.net/pdf?id=S1X7nhsxl

[Code]https://github.com/hvy/chainer-gan-denoising-feature-matching

[Sampling Generative Networks]

[Paper]https://arxiv.org/abs/1609.04468

[Code]https://github.com/dribnet/plat

[Mode Regularized Generative Adversarial Networkss]( Yoshua Bengio's paper)

[Paper]https://arxiv.org/abs/1612.02136

[How to train Gans]

[Docu]https://github.com/soumith/ganhacks#authors

[Towards Principled Methods for Training Generative Adversarial Networks] (ICLR 2017)

[Paper]http://openreview.net/forum?id=Hk4_qw5xe

[Unrolled Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1611.02163

[Code]https://github.com/poolio/unrolled_gan

[Least Squares Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1611.04076

[Code]https://github.com/pfnet-research/chainer-LSGAN

[Wasserstein GAN]

[Paper]https://arxiv.org/abs/1701.07875

[Code]https://github.com/martinarjovsky/WassersteinGAN

[Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities] (The same as WGan)

[Paper]https://arxiv.org/abs/1701.06264

[Code]https://github.com/guojunq/lsgan

[Towards Principled Methods for Training Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1701.04862

3D

[Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling] (2016 NIPS)

[Paper]https://arxiv.org/abs/1610.07584

[Web]http://3dgan.csail.mit.edu/

[code]https://github.com/zck119/3dgan-release

Face Generative and Editing

[Autoencoding beyond pixels using a learned similarity metric]

[Paper]https://arxiv.org/abs/1512.09300

[code]https://github.com/andersbll/autoencoding_beyond_pixels

[Coupled Generative Adversarial Networks] （NIPS）

[Paper]http://mingyuliu.net/

[Caffe Code]https://github.com/mingyuliutw/CoGAN

[Tensorflow Code]https://github.com/andrewliao11/CoGAN-tensorflow

[Invertible Conditional GANs for image editing]

[Paper]https://drive.google.com/file/d/0B48XS5sLi1OlRkRIbkZWUmdoQmM/view

[Code]https://github.com/Guim3/IcGAN

[Learning Residual Images for Face Attribute Manipulation]

[Paper]https://arxiv.org/abs/1612.05363

[Neural Photo Editing with Introspective Adversarial Networks](ICLR 2017)

[Paper]https://arxiv.org/abs/1609.07093

[Code]https://github.com/ajbrock/Neural-Photo-Editor

For discrete distributions

[Maximum-Likelihood Augmented Discrete Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1702.07983v1

[Boundary-Seeking Generative Adversarial Networks]

[Paper]https://arxiv.org/abs/1702.08431

[GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution]

[Paper]https://arxiv.org/abs/1611.04051

Project

[cleverhans] (A library for benchmarking vulnerability to adversarial examples)

[Code]https://github.com/openai/cleverhans

[reset-cppn-gan-tensorflow] (Using Residual Generative Adversarial Networks and Variational Auto-encoder techniques to produce high resolution images)

[Code]https://github.com/hardmaru/resnet-cppn-gan-tensorflow

[HyperGAN] (Open source GAN focused on scale and usability)

[Code]https://github.com/255bits/HyperGAN

AIJob社是《全球人工智能》旗下专门为AI开发工程师免费服务的求职平台。我们将竭尽全力帮助每一个ai工程师对接自己喜欢的企业，推荐给你喜欢的直接领导，帮你谈一个最好的薪资待遇。

微信咨询：aihr007简历投递:hr@top25.cn企业合作:job@top25.cn

《全球人工智能》招聘5名兼职翻译及10名兼职VIP社群专家：图像技术、语音技术、自然语言、机器学习、数据挖掘等专业技术领域，工作内容及待遇请在公众号内回复“兼职+个人微信号”联系工作人员。

热门文章推荐

重磅|全球AI报告：看看谷歌|苹果|Facebook等十几家巨头都收购了哪些牛逼的AI公司？