2016.11.09 13:21 字数 1551 阅读 1263评论 0喜欢 7
Goodfellow和Bengio等人发表在NIPS 2014年的文章Generative adversary network，是生成对抗网络的开创文章，论文思想启发自博弈论中的二人零和博弈。在二人零和博弈中，两位博弈方的利益之和为零或一个常数，即一方有所得，另一方必有所失。GAN模型中的两位博弈方分别由生成式模型(generative model)和判别式模型(discriminative model)充当。生成模型G捕捉样本数据的分布，判别模型D是一个二分类器，估计一个样本来自于训练数据（而非生成数据）的概率。G和D一般都是非线性映射函数，例如多层感知机、卷积神经网络等。
如图所示，左图是一个判别式模型，当输入训练数据x时，期待输出高概率（接近1）；右图下半部分是生成模型，输入是一些服从某一简单分布（例如高斯分布）的随机噪声z，输出是与训练图像相同尺寸的生成图像。向判别模型D输入生成样本，对于D来说期望输出低概率（判断为生成样本），对于生成模型G来说要尽量欺骗D，使判别模型输出高概率（误判为真实样本），从而形成竞争与对抗。
GAN.png
GAN优势很多：根据实际的结果，看上去产生了更好的样本；GAN能训练任何一种生成器网络；GAN不需要设计遵循任何种类的因式分解的模型，任何生成器网络和任何鉴别器都会有用；GAN无需利用马尔科夫链反复采样，无需在学习过程中进行推断，回避了近似计算棘手的概率的难题。
GAN主要存在的以下问题：网络难以收敛，目前所有的理论都认为GAN应该在纳什均衡上有很好的表现，但梯度下降只有在凸函数的情况下才能保证实现纳什均衡。
GAN从2014年到现在发展很快，特别是最近ICLR 2016/2017关于GAN的论文很多，GAN现在有很多问题还有到解决，潜力很大。总体可以将已有的GANs论文分为以下几类
GAN Theory
GAN in Semi-supervised
Muti-GAN
GAN with other Generative model
GAN with RNN
GAN in Application
此类关注与无监督GAN本身原理的研究：比较两个分布的距离；用DL的一些方法让GAN快速收敛等等。相关论文有：
GAN: Goodfellow, Ian, et al. "Generative adversarial nets." Advances in Neural Information Processing Systems. 2014.
LAPGAN: Denton, Emily L., Soumith Chintala, and Rob Fergus. "Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks." Advances in neural information processing systems. 2015.
DCGAN: Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015).
Improved GAN: Salimans, Tim, et al. "Improved techniques for training gans." arXiv preprint arXiv:1606.03498 (2016).
InfoGAN: Chen, Xi, et al. "Infogan: Interpretable representation learning by information maximizing generative adversarial nets." arXiv preprint arXiv:1606.03657(2016).**
EnergyGAN: Zhao, Junbo, Michael Mathieu, and Yann LeCun. "Energy-based Generative Adversarial Network." arXiv preprint arXiv:1609.03126 (2016).
Creswell, Antonia, and Anil A. Bharath. "Task Specific Adversarial Cost Function." arXiv preprint arXiv:1609.08661 (2016).
f-GAN: Nowozin, Sebastian, Botond Cseke, and Ryota Tomioka. "f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization." arXiv preprint arXiv:1606.00709 (2016).
Unrolled Generative Adversarial Networks, ICLR 2017 Open Review
Improving Generative Adversarial Networks with Denoising Feature Matching, ICLR 2017 Open Review
Mode Regularized Generative Adversarial Networks, ICLR 2017 Open Review
b-GAN: Unified Framework of Generative Adversarial Networks, ICLR 2017 Open Review
Mohamed, Shakir, and Balaji Lakshminarayanan. "Learning in Implicit Generative Models." arXiv preprint arXiv:1610.03483 (2016).
此类研究将GAN用于半监督学习，相关论文有：
Springenberg, Jost Tobias. "Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks." arXiv preprint arXiv:1511.06390 (2015).
Odena, Augustus. "Semi-Supervised Learning with Generative Adversarial Networks." arXiv preprint arXiv:1606.01583 (2016).
此类研究将多个GAN进行组合，相关论文有：
CoupledGAN: Liu, Ming-Yu, and Oncel Tuzel. "Coupled Generative Adversarial Networks." arXiv preprint arXiv:1606.07536 (2016).
Wang, Xiaolong, and Abhinav Gupta. "Generative Image Modeling using Style and Structure Adversarial Networks." arXiv preprint arXiv:1603.05631(2016).
Generative Adversarial Parallelization, ICLR 2017 Open Review
LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation, ICLR 2017 Open Review
此类研究将GAN与其他生成模型组合，相关论文有：
Dosovitskiy, Alexey, and Thomas Brox. "Generating images with perceptual similarity metrics based on deep networks." arXiv preprint arXiv:1602.02644(2016).
Larsen, Anders Boesen Lindbo, Søren Kaae Sønderby, and Ole Winther. "Autoencoding beyond pixels using a learned similarity metric." arXiv preprint arXiv:1512.09300 (2015).
Theis, Lucas, and Matthias Bethge. "Generative image modeling using spatial lstms." Advances in Neural Information Processing Systems. 2015.
此类研究将GAN与RNN结合（也以参考Pixel RNN），相关论文有：
Im, Daniel Jiwoong, et al. "Generating images with recurrent adversarial networks." arXiv preprint arXiv:1602.05110 (2016).
Kwak, Hanock, and Byoung-Tak Zhang. "Generating Images Part by Part with Composite Generative Adversarial Networks." arXiv preprint arXiv:1607.05387 (2016).
Yu, Lantao, et al. "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient." arXiv preprint arXiv:1609.05473 (2016).
此类研究将GAN的实际运用（不包括图像生成），相关论文有：
Zhu, Jun-Yan, et al. "Generative visual manipulation on the natural image manifold." European Conference on Computer Vision. Springer International Publishing, 2016.
Creswell, Antonia, and Anil Anthony Bharath. "Adversarial Training For Sketch Retrieval." European Conference on Computer Vision. Springer International Publishing, 2016.
Reed, Scott, et al. "Generative adversarial text to image synthesis." arXiv preprint arXiv:1605.05396 (2016).
Ravanbakhsh, Siamak, et al. "Enabling Dark Energy Science with Deep Generative Models of Galaxy Images." arXiv preprint arXiv:1609.05796(2016).
Abadi, Martín, and David G. Andersen. "Learning to Protect Communications with Adversarial Neural Cryptography." arXiv preprint arXiv:1610.06918(2016).
Odena, Augustus, Christopher Olah, and Jonathon Shlens. "Conditional Image Synthesis With Auxiliary Classifier GANs." arXiv preprint arXiv:1610.09585 (2016).
Ledig, Christian, et al. "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network." arXiv preprint arXiv:1609.04802 (2016).
Nguyen, Anh, et al. "Synthesizing the preferred inputs for neurons in neural networks via deep generator networks." arXiv preprint arXiv:1605.09304(2016).