Tue Aug 6 14:07:09 CST 2019
What I want to know
- What is GAN?
- Why does it work?
- How does learn the data distribution?
- How can it help my project?
Materials
[Thesis] Learning to Synthesize and Manipulate Natural Images (SIG18 best PhD thesis)
[Video] Introduction to GANs, NIPS 2016, Ian Goodfellow, OpenAI (30mins)
<span id='nips2h'></span>
[Video] Ian Goodfellow: Generative Adversarial Networks (NIPS 2016 tutorial) (2hrs)
[WebPage] MSRA: 到底什么是生成式對抗網(wǎng)絡(luò)GAN薇缅？
<span id="web2"></span>
[WebPage] A Beginner's Guide to Generative Adversarial Networks (GANs)
Notes
Basics
GAN網(wǎng)絡(luò)有一個生成器和一個判別器
，生成器的目標(biāo)是為了學(xué)習(xí)數(shù)據(jù)分布梧奢，判別器的目標(biāo)是判定輸入的數(shù)據(jù)是否符合真實(shí)分布惦蚊。
優(yōu)化方程
網(wǎng)絡(luò)的兩個部分
input noise
->
-> x sampled from
->
->
,
x sampled from data ->
Training
最直觀的處理辦法就是分別對D和g進(jìn)行交互迭代铣焊，固定g逊朽，優(yōu)化D，一段時間后粗截，固定D再優(yōu)化g惋耙，直到過程收斂。
High level understanding
Basically, GAN consists of a generator and a discriminator. The generator takes a feature vector, which in this case is random noise, and outputs a sample that mimics the data distribution. The discriminator takes a sample either from the original data or generated by generator, its job is to successfully distinguish real ones from fake ones.
As shown in the following figure, discriminator is supervised by ground truth label, while the generator is supervised by discriminator.
[圖片上傳失敗...(image-68adc6-1647766988833)]
Looking at it separately, the discriminator does a standard binary classification task, real or fake. The network returns a probability, a number between 0 and 1, with 1 representing a prediction of authenticity and 0 representing fake.
The generator takes a feature and expands it to a data sample. It is the opposite process of discriminator. The goal of a generator is to learn the data distribution, how to tell if you have successfully learned the distribution? The generator generates data from random noise, if the discriminator thinks it is real, the generator can be said to have learned the real distribution of the dataset.
The question a generative algorithm tries to answer is: Assuming this email is spam, how likely are these features (words it contains)? While discriminative models care about the relation between
(label) and
(data), generative models care about “how you get
, the probability of
The discriminator, on the other hand, captures , the probability of
given
. Which is given an email (words it contains), how likely the email is spam.
GANs, Encoder-decoder, Autoencoders and VAEs
The generator in GAN serves the similar function as a decoder in Encoder-decoder network??? What are the differences.
[quote]
You can bucket generative algorithms into one of three types:
- Given a label, they predict the associated features (Naive Bayes)
- Given a hidden representation, they predict the associated features (VAE, GAN)
- Given some of the features, they predict the rest (inpainting, imputation)
Applications
- Same domain
- super resolution
- image filling / repairing
- Cross domain transfer
- 2d to 3d
- text to image
- picture style transfer
- Learn joint distribution
- learn attributes from images
Notes on NIPS tutorial
RoadMap
- Why study generative modeling?
- How do generative models work? How do GANs compare to others?
- How do GANs work?
- Tips and tricks
- Research frontiers
- Combining GANs with other methods
