2016.11.09 13:21 字數 1551 閱讀 1263評論 0喜歡 7
Goodfellow和Bengio等人發表在NIPS 2014年的文章Generative adversary network，是生成對抗網絡的開創文章，論文思想啟發自博弈論中的二人零和博弈。在二人零和博弈中，兩位博弈方的利益之和為零或一個常數，即一方有所得，另一方必有所失。GAN模型中的兩位博弈方分别由生成式模型(generative model)和判别式模型(discriminative model)充當。生成模型G捕捉樣本資料的分布，判别模型D是一個二分類器，估計一個樣本來自于訓練資料（而非生成資料）的機率。G和D一般都是非線性映射函數，例如多層感覺機、卷積神經網絡等。
如圖所示，左圖是一個判别式模型，當輸入訓練資料x時，期待輸出高機率（接近1）；右圖下半部分是生成模型，輸入是一些服從某一簡單分布（例如高斯分布）的随機噪聲z，輸出是與訓練圖像相同尺寸的生成圖像。向判别模型D輸入生成樣本，對于D來說期望輸出低機率（判斷為生成樣本），對于生成模型G來說要盡量欺騙D，使判别模型輸出高機率（誤判為真實樣本），進而形成競争與對抗。
GAN.png
GAN優勢很多：根據實際的結果，看上去産生了更好的樣本；GAN能訓練任何一種生成器網絡；GAN不需要設計遵循任何種類的因式分解的模型，任何生成器網絡和任何鑒别器都會有用；GAN無需利用馬爾科夫鍊反複采樣，無需在學習過程中進行推斷，回避了近似計算棘手的機率的難題。
GAN主要存在的以下問題：網絡難以收斂，目前所有的理論都認為GAN應該在納什均衡上有很好的表現，但梯度下降隻有在凸函數的情況下才能保證實作納什均衡。
GAN從2014年到現在發展很快，特别是最近ICLR 2016/2017關于GAN的論文很多，GAN現在有很多問題還有到解決，潛力很大。總體可以将已有的GANs論文分為以下幾類
GAN Theory
GAN in Semi-supervised
Muti-GAN
GAN with other Generative model
GAN with RNN
GAN in Application
此類關注與無監督GAN本身原理的研究：比較兩個分布的距離；用DL的一些方法讓GAN快速收斂等等。相關論文有：
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).
此類研究将GAN用于半監督學習，相關論文有：
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).
此類研究将多個GAN進行組合，相關論文有：
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
此類研究将GAN與其他生成模型組合，相關論文有：
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.
此類研究将GAN與RNN結合（也以參考Pixel RNN），相關論文有：
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).
此類研究将GAN的實際運用（不包括圖像生成），相關論文有：
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).