7月27日深度学习笔记——GAN

---

前言

本文为7月27日深度学习笔记， 分为三个章节：

• Basic Idea of GAN：Generator vs. Disciminator、Can Generator learn by itself——Yes、Can Discriminator generate——Yes；
• Conditional Generation by GAN：Conditional GAN；
• Unsupervised Conditional Generation：Approach 1：Direct Transformation、Approach 2：Projection to Common Space.

---

一、Basic Idea of GAN

1、Generator vs. Disciminator

(1)、Generator

Learn to generate the object at the component level.

(3)、Discriminator

Evaluate the whole object, and find the best one.

(3)、Algorithm

• Initialize generator(G) and discriminator(D)；
• In each training iteration:
  1. 固定 G，更新 D，discriminator learns to assign high scores to real objects and low scores to generated objects.
     
  2. 固定 D，更新 G，Generator learns to “fool” the discriminator：

• Learning D：

  • Sample m examples { x 1 , x 2 , … , x m } \{x^1, x^2, …, x^m\} {x1,x2,…,xm} from database;
  • Sample m noise samples { z 1 , z 2 , … , z m } \{z^1, z^2, …, z^m\} {z1,z2,…,zm} from a distribution;
  • Obtaining generated data { x ~ 1 , x ~ 2 , … , x ~ m } , x ~ i = G ( z i ) \{\tilde{x}^1, \tilde{x}^2, …, \tilde{x}^m\}, \tilde{x}^i = G(z^i) {x~1,x~2,…,x~m},x~i=G(zi);
  • Update discriminator parameters ${\theta }_d$ to maximize:
    1. $\tilde{V}=\frac{1}{m}{\sum }_{i=1}^{m}logD(x^i)+\frac{1}{m}{\sum }_{i=1}^{m}log(1-D({\tilde{x}}^i));$
    2. ${\theta }_d+\eta ▽\tilde{V}({\theta }_d)\to {\theta }_{d+1}$

• Learning G：

  • Sample m noise samples { z 1 , z 2 , … , z m } \{z^1, z^2, …, z^m\} {z1,z2,…,zm} from a distribution;
  • Update generator parameters ${\theta }_g$ to maximize:
    1. $\tilde{V}=\frac{1}{m}{\sum }_{i=1}^{m}log(D(G(z^i)));$
    2. ${\theta }_g+\eta ▽\tilde{V}({\theta }_g)\to {\theta }_{g+1}.$

(4)、Pros.&Cons.

\	Generator	Discriminator
Pros	- Easy to generate even with deep model.	Considering the big picture
Cons	- Imitate the appearance; - Hard to learn the correlation between components	- Generation is not always feasible; - Especially when your model is deep;

2、Can Generator learn by itself——Yes

NN Decoder = Generator.

3、Can Discriminator generate——Yes

Discriminator is a function D:
$$D:X\to R$$

• Input: an image;
• Output $D(x)$: scalar which represents how “good” an object x is.

---

二、Conditional Generation by GAN

1、Conditional GAN

(1)、Traditional supervised approach

(2)、Discriminator

---

三、Unsupervised Conditional Generation

Transform an object from one domain to another without paired data.

1、Approach 1：Direct Transformation

2、Approach 2：Projection to Common Space

---