点击上方“专知”关注获取更多AI知识!
【导读】当地时间 10月 22 日到10月29日,两年一度的计算机视觉国际顶级会议 International Conference on Computer Vision(ICCV 2017)在意大利威尼斯开幕。Google Brain 研究科学家 Ian Goodfellow 在会上作为主题为《生成对抗网络(Generative Adversarial Networks)》的Tutorial 最新演讲, 介绍了GAN的原理和最新的应用。昨天我们介绍了此内容,请查看
【干货】Google GAN之父Ian Goodfellow ICCV2017演讲:解读生成对抗网络的原理与应用
今天专知内容组特此整理了GAN的知识资料大全,为大家呈上,欢迎查看。
理论学习
训练GANs的技巧 | http://papers.nips.cc/paper/6124-improved-techniques-for-training-gans.pdf |
Energy-Based GANs 以及Yann Le Cun 的相关研究 | http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf |
模式正则化GAN | https://arxiv.org/pdf/1612.02136.pdf |
最新NIPS2016也有最新的关于训练GAN模型的总结 | https://github.com/soumith/ganhacks |
The GAN Zoo千奇百怪的生成对抗网络,都在这里了。你没看错,里面已经有有近百个了。 | https://github.com/hindupuravinash/the-gan-zoo |
报告
Ian Goodfellow的GANs报告ICCV 2017 | https://pan.baidu.com/s/1bpIZvfL |
Ian Goodfellow的GANs报告ICCV 2017的中文讲稿 | https://mp.weixin.qq.com/s/nPBFrnO3_QJjAzm37G5ceQ |
Ian Goodfellow的GANs报告NIPS 2016 | http://www.iangoodfellow.com/slides/2016-12-04-NIPS.pdf |
Ian Goodfellow的GANs报告NIPS 2016 的中文讲稿 | http://www.sohu.com/a/121189842_465975 |
Russ Salakhutdinov的深度生成模型 | http://www.cs.toronto.edu/~rsalakhu/talk_Montreal_2016_Salakhutdinov.pdf |
课程
NIPS 2016教程:生成对抗网络 | https://arxiv.org/pdf/1701.00160.pdf |
训练GANs的技巧和窍门 | https://github.com/soumith/ganhacks |
OpenAI生成模型 | https://blog.openai.com/generative-models/ |
用Keras实现MNIST生成对抗模型 | https://oshearesearch.com/index.PHP/2016/07/01/mnist-generative-adversarial-model-in-keras/ |
用深度学习TensorFlow实现图像修复 | http://bamos.github.io/2016/08/09/deep-completion/ |
中文教程
生成对抗网络初学入门:一文读懂GAN的基本原理 | http://www.xtecher.com/Xfeature/view?aid=7496 |
深入浅出:GAN原理与应用入门介绍 | https://zhuanlan.zhihu.com/p/28731033 |
港理工在读博士李嫣然深入浅出GAN之应用篇 | https://pan.baidu.com/s/1o8n4UDk 密码: 78wt |
中科院自动化所 中文综述 《生成式对抗网络 GAN 的研究进展与展望》 | https://pan.baidu.com/s/1dEMITo9 密码: qqcc |
萌物生成器:如何使用四种GAN制造猫图 | https://zhuanlan.zhihu.com/p/27769807 |
GAN学习指南:从原理入门到制作生成Demo | https://zhuanlan.zhihu.com/p/24767059x |
生成式对抗网络GAN研究进展 | http://blog.csdn.net/solomon1558/article/details/52537114 |
生成对抗网络(GAN)的前沿进展(论文、报告、框架和Github资源)汇总 | http://blog.csdn.net/love666666shen/article/details/74953970 |
综述
中科院自动化所 中文综述 《生成式对抗网络 GAN 的研究进展与展望》 | 参考链接: https://pan.baidu.com/s/1dEMITo9 密码: qqcc |
Github 资源
深度卷积生成对抗模型(DCGAN) | https://github.com/Newmu/dcgan_code |
TensorFlow实现深度卷积生成对抗模型(DCGAN) | https://github.com/carpedm20/DCGAN-tensorflow |
Torch实现深度卷积生成对抗模型(DCGAN) | https://github.com/soumith/dcgan.torch |
Keras实现深度卷积生成对抗模型(DCGAN) | https://github.com/jacobgil/keras-dcgan |
使用神经网络生成自然图像(Facebook的Eyescream项目) | https://github.com/facebook/eyescream |
对抗自编码(AdversarialAutoEncoder) | https://github.com/musyoku/adversarial-autoencoder |
利用ThoughtVectors 实现文本到图像的合成 | https://github.com/paarthneekhara/text-to-image |
对抗样本生成器(Adversarialexample generator) | https://github.com/e-lab/torch-toolbox/tree/master/Adversarial |
深度生成模型的半监督学习 | https://github.com/dpkingma/nips14-ssl |
GANs的训练方法 | https://github.com/openai/improved-gan |
生成式矩匹配网络(Generative Moment Matching Networks, GMMNs) | https://github.com/yujiali/gmmn |
对抗视频生成 | https://github.com/dyelax/Adversarial_Video_Generation |
基于条件对抗网络的图像到图像翻译(pix2pix) | https://github.com/phillipi/pix2pix |
对抗机器学习库Cleverhans | https://github.com/openai/cleverhans |
最新论文
基于深度卷积生成对抗网络的无监督学习(Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (DCGANs))2015 | https://arxiv.org/pdf/1511.06434v2.pdf |
对抗实例的解释和利用(Explaining and Harnessing Adversarial Examples)2014 | https://arxiv.org/pdf/1412.6572.pdf |
基于深度生成模型的半监督学习( Semi-Supervised Learning with Deep Generative Models )2014 | https://arxiv.org/pdf/1406.5298v2.pdf |
基于拉普拉斯金字塔生成式对抗网络的深度图像生成模型(Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks)2015 | http://papers.nips.cc/paper/5773-deep-generative-image-models-using-a-5. |
http://papers.nips.cc/paper/5773-deep-generative-image-models-using-a-5. | https://arxiv.org/pdf/1606.03498v1.pdf |
条件生成对抗网络(Conditional Generative Adversarial Nets)2014 | https://arxiv.org/pdf/1411.1784v1.pdf |
生成式矩匹配网络(Generative Moment Matching Networks)2015 | http://proceedings.mlr.press/v37/li15.pdf |
超越均方误差的深度多尺度视频预测(Deep multi-scale video prediction beyond mean square error)2015 | https://arxiv.org/pdf/1511.05440.pdf |
通过学习相似性度量的超像素自编码(Autoencoding beyond pixels using a learned similarity metric)2015 | https://arxiv.org/pdf/1512.09300.pdf |
对抗自编码(Adversarial Autoencoders)2015 | https://arxiv.org/pdf/1511.05644.pdf |
InfoGAN:基于信息最大化GANs的可解释表达学习(InfoGAN:Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets)2016 | https://arxiv.org/pdf/1606.03657v1.pdf |
上下文像素编码:通过修复进行特征学习(Context Encoders: Feature Learning by Inpainting)2016 | http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Pathak_Context_Encoders_Feature_CVPR_2016_paper.pdf |
http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Pathak_Context_Encoders_Feature_CVPR_2016_paper.pdf | http://proceedings.mlr.press/v48/reed16.pdf |
基于像素卷积神经网络的条件生成图片(Conditional Image Generation with PixelCNN Decoders)2015 | https://arxiv.org/pdf/1606.05328.pdf |
对抗特征学习(Adversarial Feature Learning)2016 | https://arxiv.org/pdf/1605.09782.pdf |
结合逆自回归流的变分推理(Improving Variational Inference with Inverse Autoregressive Flow )2016 | https://papers.nips.cc/paper/6581-improving-variational-autoencoders-with-inverse-autoregressive-flow.pdf |
深度学习系统对抗样本黑盒攻击(Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples)2016 | https://arxiv.org/pdf/1602.02697.pdf |
参加,推断,重复:基于生成模型的快速场景理解(Attend, infer, repeat: Fast scene understanding with generative models)2016 | https://arxiv.org/pdf/1603.08575.pdf |
f-GAN: 使用变分散度最小化训练生成神经采样器(f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization )2016 | http://papers.nips.cc/paper/6066-tagger-deep-unsupervised-perceptual-grouping.pdf |
在自然图像流形上的生成视觉操作(Generative Visual Manipulation on the Natural Image Manifold)2016 | https://arxiv.org/pdf/1609.03552.pdf |
通过平均差异最大优化训练生成神经网络(Training generative neural networks via Maximum Mean Discrepancy optimization)2015 | https://arxiv.org/pdf/1505.03906.pdf |
对抗性推断学习(Adversarially Learned Inference)2016 | https://arxiv.org/pdf/1606.00704.pdf |
基于循环对抗网络的图像生成(Generating images with recurrent adversarial networks)2016 | https://arxiv.org/pdf/1602.05110.pdf |
生成对抗模仿学习(Generative Adversarial Imitation Learning)2016 | http://papers.nips.cc/paper/6391-generative-adversarial-imitation-learning.pdf |
基于3D生成对抗模型学习物体形状的概率隐空间(Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling)2016 | https://arxiv.org/pdf/1610.07584.pdf |
学习画画(Learning What and Where to Draw)2016 | https://arxiv.org/pdf/1610.02454v1.pdf |
基于辅助分类器GANs的条件图像合成(Conditional Image Synthesis with Auxiliary Classifier GANs)2016 | https://arxiv.org/pdf/1610.09585.pdf |
隐生成模型的学习(Learning in Implicit Generative Models)2016 | https://arxiv.org/pdf/1610.03483.pdf |
VIME: 变分信息最大化探索(VIME: Variational Information Maximizing Exploration)2016 | http://papers.nips.cc/paper/6591-vime-variational-information-maximizing-exploration.pdf |
生成对抗网络的展开(Unrolled Generative Adversarial Networks)2016 | https://arxiv.org/pdf/1611.02163.pdf |
训练生成对抗网络的基本方法(Towards Principled Methods for Training Generative Adversarial Networks)2017 | https://arxiv.org/pdf/1701.04862.pdf |
基于内省对抗网络的神经图像编辑(Neural Photo Editing with Introspective Adversarial Networks)2016 | https://arxiv.org/pdf/1609.07093.pdf |
基于解码器的生成模型的定量分析(On the Quantitative Analysis of Decoder-Based Generative Models )2016 | https://arxiv.org/pdf/1611.04273.pdf |
结合生成对抗网络和Actor-Critic 方法(Connecting Generative Adversarial Networks and Actor-Critic Methods)2016 | https://arxiv.org/pdf/1610.01945.pdf |
通过对抗网络使用模拟和非监督图像训练( Learning from Simulated and Unsupervised Images through Adversarial Training)2016 | https://arxiv.org/pdf/1612.07828.pdf |
基于上下文RNN-GANs的抽象推理图的生成(Contextual RNN-GANs for Abstract Reasoning Diagram Generation)2016 | https://arxiv.org/pdf/1609.09444.pdf |
生成多对抗网络(Generative Multi-Adversarial Networks)2016 | https://arxiv.org/pdf/1611.01673.pdf |
生成对抗网络组合(Ensembles of Generative Adversarial Network)2016 | https://arxiv.org/pdf/1612.00991.pdf |
改进生成器目标的GANs(Improved generator objectives for GANs) 2016 | https://arxiv.org/pdf/1612.02780.pdf |
生成对抗模型的隐向量精准修复(Precise Recovery of Latent Vectors from Generative Adversarial Networks)2017 | https://openreview.NET/pdf?id=HJC88BzFl |
生成混合模型(Generative Mixture of Networks)2017 | https://arxiv.org/pdf/1702.03307.pdf |
记忆生成时空模型(Generative Temporal Models with Memory)2017 | https://arxiv.org/pdf/1702.04649.pdf |
停止GAN暴力:生成性非对抗模型(Stopping GAN Violence: Generative Unadversarial Networks)2017 | https://arxiv.org/pdf/1703.02528.pdf |
特注:
请登录www.zhuanzhi.ai或者点击阅读原文,
顶端搜索“GAN” 主题,直接获取查看获得全网收录资源进行查看, 涵盖论文等资源下载链接,并获取更多与强化学习的知识资料!如下图所示。
此外,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“GAN2” 就可以获取专知内容组整理的知识资料全集pdf文档!
回复“GAN” 可以获取专知内容组整理的就可以获取Ian Goodfellow的slide!
欢迎转发到你的微信群和朋友圈,分享专业AI知识!
获取更多关于机器学习以及人工智能知识资料,请访问www.zhuanzhi.ai, 或者点击阅读原文,即可得到!
-END-
欢迎使用专知
专知,一个新的认知方式!目前聚焦在人工智能领域为AI从业者提供专业可信的知识分发服务, 包括主题定制、主题链路、搜索发现等服务,帮你又好又快找到所需知识。
使用方法>>访问www.zhuanzhi.ai, 或点击文章下方“阅读原文”即可访问专知
中国科学院自动化研究所专知团队
@2017 专知
专 · 知
关注我们的公众号,获取最新关于专知以及人工智能的资讯、技术、算法、深度干货等内容。扫一扫下方关注我们的微信公众号。
点击“阅读原文”,使用专知!