AdversarialNetsPapers

The classical Papers about adversarial nets [Codes]: https://github.com/wiseodd/generative-models

The First paper

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

Representation Learning

1. [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks][Paper][Code](Gan with convolutional networks)(ICLR)
2. [Adversarial Autoencoders][Paper][Code]
3. Generative Adversarial Networks as Variational Training of Energy Based Models](http://www.mathpubs.com/detail/1611.01799v1/Generative-Adversarial-Networks-as-Variational-Training-of-Energy-Based-Models)(ICLR 2017)
4. [Learning from Simulated and Unsupervised Images through Adversarial Training][Paper][code]（Apple paper）
5. [Adversarial Feature Learning][Paper]
6. [Generalization and Equilibrium in Generative Adversarial Nets (GANs)][Paper][Video]

Image Generation

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

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

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

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

5. [Adversarial Training for Sketch Retrieval][Paper]

6. [Generative Image Modeling using Style and Structure Adversarial Networks][Paper][[Code]](https://github.com/xiaolonw/ss-gan

7. [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks][Paper][Code]

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

   ​

Image-to-Image Translation

1. [Generative Visual Manipulation on the Natural Image Manifold][Paper][Code]
2. [Image-to-image translation using conditional adversarial nets][Paper][Code][Code]
3. [Pixel-Level Domain Transfer][Paper][Code]
4. [Invertible Conditional GANs for image editing][Paper][Code]
5. [Unsupervised Image-to-Image Translation with Generative Adversarial Networks][Paper]
6. [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks][Paper][Code]

Test-to-Image Generation

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

Ensemble

1. [AdaGAN: Boosting Generative Models][Paper][[Code]]（Google Brain）

Clustering

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

Image Inpainting

1. [Semantic Image Inpainting with Perceptual and Contextual Losses][Paper][Code]
2. [Context Encoders: Feature Learning by Inpainting][Paper][Code]
3. [Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks][Paper]

Joint Probability

1. [Adversarially Learned Inference][Paper][Code]

Super-Resolution

1. [Image super-resolution through deep learning ][Code](Just for face dataset)
2. [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network][Paper][Code]（Using Deep residual network）
3. [EnhanceGAN][Docs][[Code]]

Disocclusion

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

Semantic Segmentation

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

Object Detection

1. [Perceptual generative adversarial networks for small object detection][[Paper]]（Submitted）
2. [A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection][Paper](CVPR2017)

RNN

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

Conditional adversarial

1. [Conditional Generative Adversarial Nets][Paper][Code]
2. [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets][Paper][Code]
3. [Conditional Image Synthesis With Auxiliary Classifier GANs][Paper][Code](GoogleBrain ICLR 2017)

Video Prediction

1. [Deep multi-scale video prediction beyond mean square error][Paper][Code](Yann LeCun's paper)
2. [Unsupervised Learning for Physical Interaction through Video Prediction][Paper](Ian Goodfellow's paper)
3. [Generating Videos with Scene Dynamics][Paper][Web][Code]

Texture Synthesis & style transfer

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

GAN Theory

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

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

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

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

5. [Sampling Generative Networks] [Paper][Code]

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

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

8. [Unrolled Generative Adversarial Networks] [Paper][Code]

9. [Least Squares Generative Adversarial Networks] [Paper][Code]

10. [Wasserstein GAN] [Paper][Code]

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

12. [BEGAN: Boundary Equilibrium Generative Adversarial Networks] [Paper]

• "New equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks."

13. [Improved Training of Wasserstein GANs][Paper]

• "Our proposed method converges faster and generates higher-quality samples than WGAN with weight clipping."

14. [Adversarial Generator-Encoder Networks][Paper][Code]

15. [Adversarial Machine Learning at Scale][Paper]

3D

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

Implementation Guidelines

1. [How to train Gans] [Docu]

Face Generative and Editing

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

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

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

4. [Learning Residual Images for Face Attribute Manipulation] [Paper]

5. [Neural Photo Editing with Introspective Adversarial Networks] [Paper][Code](ICLR 2017)

For discrete distributions

1. [Maximum-Likelihood Augmented Discrete Generative Adversarial Networks] [Paper]

2. [Boundary-Seeking Generative Adversarial Networks] [Paper]

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

Project

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

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

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

Blogs

Author	Address
inFERENCe	Adversarial network
inFERENCe	InfoGan
distill	Deconvolution and Image Generation
yingzhenli	Gan theory
OpenAI	Generative model

Other

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

[2] [PDF](NIPS Lecun Slides)