【推荐】GAN架构入门综述(资源汇总)

2017 年 9 月 3 日 机器学习研究会
【推荐】GAN架构入门综述(资源汇总)


点击上方 “机器学习研究会”可以订阅
摘要
 

转自:爱可可-爱生活

Introduction

How do you teach a machine to draw a human face if it has never seen one? A computer can store petabytes of photos, but it has no idea what gives a bunch of pixels a meaning related to someone’s appearance.

For many years this problem has been tackled by various generative models. They used different assumptions, often too strong to be practical, to model the underlying distribution of the data.

The results were suboptimal for most of the tasks we have now. Text generated with Hidden Markov Models was very dull and predictable, images from Variational Autoencoders were blurry and, despite the name, lacked variety. All those shortcomings called for an entirely new approach, and recently such method was invented.

In this article, we aim to give a comprehensive introduction to general ideas behind Generative Adversarial Networks (GANs), show you the main architectures that would be good starting points and provide you with an armory of tricks that would significantly improve your results.

Towards the invention of GANs

The basic idea of a generative model is to take a collection of training examples and form a representation of their probability distribution. And the usual method for it was to infer a probability density function directly.

When I was studying generative models the first time I couldn't help but wonder - why bother with them when we have so many real life training examples already? The answer was quite compelling, here are just a few of possible applications that call for a good generative model:

  1. Simulate possible outcomes of an experiment, cutting costs and speeding up the research.

  2. Action planning using predicted future states - imagine a GAN that "knows" the road situation the next moment.

  3. Generating missing data and labels - we often lack the clean data in the right format, and it causes overfitting.

  4. High-quality speech generation

  5. Automated quality improvement for photos (Image Super-Resolution)

In 2014, Ian Goodfellow and his colleagues from University of Montreal introduced Generative Adversarial Networks (GANs). It was a novel method of learning an underlying distribution of the data that allowed generating artificial objects that looked strikingly similar to those from the real life.

The idea behind the GANs is very straightforward. Two networks -- a Generator and a Discriminator play a game against each other. The objective of the Generator is to produce an object, say, a picture of a person, that would look like a real one. The goal of the Discriminator is to be able to tell the difference between generated and real images.

This illustration gives a rough overview of the Generative Adversarial Network. For the moment it's most important to understand that the GAN is rather a way to make two networks work together - and both Generator and Discriminator have their own architecture. To better understand where this idea came from we will need to recall some basic algebra and ask ourselves - how can we fool a neural network that classifies images better than most humans?

Adversarial examples

Before we get to describing GANs in details, let’s take a look at a similar topic. Given a trained classifier, can we generate a sample that would fool the network? And if we do, how would it look like?

It turns out, we can.

Even more - for virtually any given image classifier it’s possible to morph an image into another, which would be misclassified with high confidence while being visually indistinguishable from the original! Such process is called an adversarial attack, and the simplicity of the generating method explains quite a lot about GANs.
An adversarial example in an example carefully computed with the purpose to be misclassified. Here is an illustration of this process. The panda on the left in indistinguishable from the one on the right - and yet it's classified as a gibbon.

链接:

https://sigmoidal.io/beginners-review-of-gan-architectures/


原文链接:

https://m.weibo.cn/3193816967/4146423228075680

“完整内容”请点击【阅读原文】
↓↓↓
登录查看更多
8

相关内容

GAN:生成性对抗网,深度学习模型的一种,在神经网络模型中引入竞争机制,非常流行。
小贴士
相关资讯
移动端机器学习资源合集
专知
3+阅读 · 2019年4月21日
【推荐】ResNet, AlexNet, VGG, Inception:各种卷积网络架构的理解
机器学习研究会
16+阅读 · 2017年12月17日
分布式TensorFlow入门指南
机器学习研究会
4+阅读 · 2017年11月28日
【推荐】自然语言处理(NLP)指南
机器学习研究会
30+阅读 · 2017年11月17日
【推荐】深度学习目标检测全面综述
机器学习研究会
17+阅读 · 2017年9月13日
【推荐】深度学习目标检测概览
机器学习研究会
9+阅读 · 2017年9月1日
【推荐】全卷积语义分割综述
机器学习研究会
17+阅读 · 2017年8月31日
【推荐】SVM实例教程
机器学习研究会
12+阅读 · 2017年8月26日
【推荐】图像分类必读开创性论文汇总
机器学习研究会
14+阅读 · 2017年8月15日
相关VIP内容
专知会员服务
32+阅读 · 2020年3月19日
【开源书】PyTorch深度学习起步,零基础入门(附pdf下载)
专知会员服务
61+阅读 · 2019年10月26日
【深度学习视频分析/多模态学习资源大列表】
专知会员服务
53+阅读 · 2019年10月16日
开源书:PyTorch深度学习起步
专知会员服务
20+阅读 · 2019年10月11日
强化学习最新教程,17页pdf
专知会员服务
45+阅读 · 2019年10月11日
[综述]深度学习下的场景文本检测与识别
专知会员服务
29+阅读 · 2019年10月10日
机器学习入门的经验与建议
专知会员服务
28+阅读 · 2019年10月10日
TensorFlow 2.0 学习资源汇总
专知会员服务
28+阅读 · 2019年10月9日
机器学习相关资源(框架、库、软件)大列表
专知会员服务
14+阅读 · 2019年10月9日
相关论文
A Survey on Bayesian Deep Learning
Hao Wang,Dit-Yan Yeung
38+阅读 · 2020年7月2日
Yash Srivastava,Vaishnav Murali,Shiv Ram Dubey,Snehasis Mukherjee
4+阅读 · 2019年8月27日
Sneha Chaudhari,Gungor Polatkan,Rohan Ramanath,Varun Mithal
11+阅读 · 2019年4月5日
A Probe into Understanding GAN and VAE models
Jingzhao Zhang,Lu Mi,Macheng Shen
6+阅读 · 2018年12月13日
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
David Bau,Jun-Yan Zhu,Hendrik Strobelt,Bolei Zhou,Joshua B. Tenenbaum,William T. Freeman,Antonio Torralba
11+阅读 · 2018年12月8日
A Survey on Deep Transfer Learning
Chuanqi Tan,Fuchun Sun,Tao Kong,Wenchang Zhang,Chao Yang,Chunfang Liu
10+阅读 · 2018年8月6日
Karol Kurach,Mario Lucic,Xiaohua Zhai,Marcin Michalski,Sylvain Gelly
3+阅读 · 2018年7月12日
Ayush Singh,Ritu Palod
4+阅读 · 2018年4月10日
Zhou Yin,Wei-Shi Zheng,Ancong Wu,Hong-Xing Yu,Hai Wang,Jianhuang Lai
7+阅读 · 2018年2月6日
Yunjey Choi,Minje Choi,Munyoung Kim,Jung-Woo Ha,Sunghun Kim,Jaegul Choo
4+阅读 · 2017年11月24日
Top