(转) AdversarialNetsPapers

简介:  本文转自:https://github.com/zhangqianhui/AdversarialNetsPapersAdversarialNetsPapersThe classical Papers about adversarial netsThe First pap...

 

 
本文转自:https://github.com/zhangqianhui/AdversarialNetsPapers

AdversarialNetsPapers

The classical Papers about adversarial nets

The First paper

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

Unclassified

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

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

 [Adversarial Autoencoders] [Paper][Code]

 [Generating images with recurrent adversarial networks] [Paper][Code]

 [Generative Visual Manipulation on the Natural Image Manifold] [Paper][Code]

 [Neural Photo Editing with Introspective Adversarial Networks] [Paper]

 [Generative Adversarial Text to Image Synthesis] [Paper][Code][code]

 [Learning What and Where to Draw] [Paper][Code]

 [Adversarial Training for Sketch Retrieval] [Paper]

 [Generative Image Modeling using Style and Structure Adversarial Networks] [Paper][Code]

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

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

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

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

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

 [SalGAN: Visual Saliency Prediction with Generative Adversarial Networks] [Paper][Code]

Image Inpainting

 [Semantic Image Inpainting with Perceptual and Contextual Losses] [Paper][Code]

 [Context Encoders: Feature Learning by Inpainting] [Paper][Code]

Super-Resolution

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

Disocclusion

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

Semantic Segmentation

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

Object Detection

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

RNN

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

Conditional adversarial

 [Conditional Generative Adversarial Nets] [Paper][Code]

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

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

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

 [Pixel-Level Domain Transfer] [Paper][Code]

 [Invertible Conditional GANs for image editing] [Paper][Code]

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

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

Video Prediction

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

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

 [Generating Videos with Scene Dynamics] [Paper][Web][Code]

Texture Synthesis && style transfer

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

GAN Theory

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

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

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

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

 [Sampling Generative Networks] [Paper][Code]

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

 [How to train Gans] [Docu]

3D

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

Face Generative

 [Autoencoding beyond pixels using a learned similarity metric] [Paper][code]

 [Coupled Generative Adversarial Networks] [Paper][Caffe Code][Tensorflow Code](NIPS)

Adversarial Examples

 [Intriguing properties of neural networks] [Paper]

 [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images] [Paper]

 [Explaining and Harnessing Adversarial Examples] [Paper]

 [Adversarial examples in the physical world] [Paper]

 [Universal adversarial perturbations ] [Paper]

 [Robustness of classifiers: from adversarial to random noise ] [Paper]

 [DeepFool: a simple and accurate method to fool deep neural networks] [Paper]

 [2] [PDF] (NIPS Goodfellow Slides)

Project

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

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

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

Blogs

 [1] http://www.inference.vc/

 [2] http://distill.pub/2016/deconv-checkerboard/

Other

 [1] http://www.iangoodfellow.com/slides/2016-12-04-NIPS.pdf (NIPS Goodfellow Slides)[Chinese Trans][details]

 [2] [PDF](NIPS Lecun Slides)

 
相关文章
[Papers]NSE, $u$, Lorentz space [Bjorland-Vasseur, JMFM, 2011]
$$\bex \int_0^T\frac{\sen{\bbu}_{L^{q,\infty}}^p}{\ve+\ln \sex{e+\sen{\bbu}_{L^\infty}}}\rd s
640 0
[Papers]NSE, $u$, Lorentz space [Sohr, JEE, 2001]
$$\bex \bbu\in L^{p,r}(0,T;L^{q,\infty}(\bbR^3)),\quad\frac{2}{p}+\frac{3}{q}=1,\quad 3
1041 0
[Papers]NSE, $u$, Lorentz space [Bosia-Pata-Robinson, JMFM, 2014]
$$\bex \bbu\in L^p(0,T;L^{q,\infty}),\quad \frac{2}{p}+\frac{3}{q}=1,\quad 3
786 0
[Papers]NSE, $\p_3u$, multiplier spaces [Guo-Gala, ANAP, 2013]
$$\bex \p_3\bbu\in L^\frac{2}{1-r}(0,T;\dot X_r(\bbR^3)),\quad 0\leq r\leq 1. \eex$$
687 0
[Papers]NSE, $\n u_3$, Lebesgue space, [Pokorny, EJDE, 2003; Zhou, MAA, 2002]
$$\bex \n u_3\in L^p(0,T;L^q(\bbR^3)),\quad \frac{2}{p}+\frac{3}{q}=\frac{3}{2},\quad 2\leq q\leq \infty. \eex$$
707 0
[Papers]NSE, $u_3$, Lebesgue space [Kukavica-Ziane, Nonlinearity, 2006]
$$\bex u_3\in L^p(0,T;L^q(\bbR^3)),\quad \frac{2}{p}+\frac{3}{q}=\frac{5}{8},\quad \frac{24}{5}
733 0