GANs最新综述论文: 生成式对抗网络及其变种如何有用【附41页pdf下载】

1 月 5 日 专知

【导读】最近一期的计算机顶级期刊ACM Computing Surveys (CSUR)出版,涵盖最新的GANs综述论文,146篇参考文献, 本文的作者来自首尔大学数据科学与人工智能实验室的师生,研究方向为深度学习和机器学习。本综述论文介绍了GAN的原理和应用。


介绍

生成对抗网络(GAN)在机器学习领域受到广泛关注,因为它们有可能学习高维,复杂的实际数据分布。具体而言,它们不依赖于关于分布的任何假设,并且可以以简单的方式从潜在空间生成真实样本。这种强大的属性使GAN可以应用于各种应用,如图像合成,图像属性编辑,图像翻译,领域适应和其他学术领域。在本文中,作者从各个角度探讨GAN的细节。此外,作者还解释了GAN如何运作以及最近提出的各种目标函数的基本含义。然后,作者将重点放在如何将GAN与自动编码器框架相结合。最后,作者列举了适用于各种任务和其他领域的GAN变体,适用于那些有兴趣利用GAN进行研究的人。


文章共分6个章节。

  1. 文章结构概述

  2. GAN的目标函数已经它各个部分是如何工作的;近几年新提出的目标函数

  3. GAN如何应用于从低维数据表示中学习一个隐空间

  4. GAN的实际应用领域

  5. GAN为什么比其他模型好

  6. 文章总结


关于GAN的结构的一些论文总结


关于GAN在不同领域与研究主题中的应用的论文总结


论文地址

https://arxiv.org/abs/1711.05914


作者Yongjun Hong,Uiwon Hwang,Jaeyoon Yoo,Sungroh Yoon

作者主页:

https://dblp.uni-trier.de/pers/hd/h/Hong:Yongjun


其他更多详情,下载全文查看:

请关注专知公众号(扫一扫最下面专知二维码,或者点击上方蓝色专知

  • 后台回复“GANVW” 就可以获取论文的下载链接~ 

  • 专知2019年1月将开设一门《深度学习:算法到实战》讲述相关GANs,欢迎报名!

专知开课啦!《深度学习: 算法到实战》, 中科院博士为你讲授!


-END-

专 · 知

   专知开课啦!《深度学习: 算法到实战》, 中科院博士为你讲授!


请加专知小助手微信(扫一扫如下二维码添加),咨询《深度学习:算法到实战》参团限时优惠报名~

欢迎微信扫一扫加入专知人工智能知识星球群,获取专业知识教程视频资料和与专家交流咨询!

请PC登录www.zhuanzhi.ai或者点击阅读原文,注册登录专知,获取更多AI知识资料!

点击“阅读原文”,了解报名专知《深度学习:算法到实战》课程

登录查看更多
点赞 0

We introduce MaSS (Momentum-added Stochastic Solver), an accelerated SGD method for optimizing over-parametrized models. Our method is simple and efficient to implement and does not require adapting hyper-parameters or computing full gradients in the course of optimization. Experimental evaluation of MaSS for several standard architectures of deep networks, including ResNet and convolutional networks, shows improved performance over Adam and SGD both in optimization and generalization. We prove accelerated convergence of MaSS over SGD and provide analysis for hyper-parameter selection in the quadratic case as well as some results in general strongly convex setting. In contrast, we show theoretically and verify empirically that the standard SGD+Nesterov can diverge for common choices of hyper-parameter values. We also analyze the practically important question of the dependence of the convergence rate and optimal hyper-parameters as functions of the mini-batch size, demonstrating three distinct regimes: linear scaling, diminishing returns and saturation.

点赞 0
阅读1+

Generating realistic images from scene graphs asks neural networks to be able to reason about object relationships and compositionality. As a relatively new task, how to properly ensure the generated images comply with scene graphs or how to measure task performance remains an open question. In this paper, we propose to harness scene graph context to improve image generation from scene graphs. We introduce a scene graph context network that pools features generated by a graph convolutional neural network that are then provided to both the image generation network and the adversarial loss. With the context network, our model is trained to not only generate realistic looking images, but also to better preserve non-spatial object relationships. We also define two novel evaluation metrics, the relation score and the mean opinion relation score, for this task that directly evaluate scene graph compliance. We use both quantitative and qualitative studies to demonstrate that our pro-posed model outperforms the state-of-the-art on this challenging task.

点赞 0
阅读1+

We present LR-GAN: an adversarial image generation model which takes scene structure and context into account. Unlike previous generative adversarial networks (GANs), the proposed GAN learns to generate image background and foregrounds separately and recursively, and stitch the foregrounds on the background in a contextually relevant manner to produce a complete natural image. For each foreground, the model learns to generate its appearance, shape and pose. The whole model is unsupervised, and is trained in an end-to-end manner with gradient descent methods. The experiments demonstrate that LR-GAN can generate more natural images with objects that are more human recognizable than DCGAN.

点赞 0
阅读2+
小贴士
Top