Understanding GAN: A Clear Explanation

The storm of GANs has swept through the entire deep learning community, making any task seem high-end as soon as it is wrapped in a GAN shell. So, what exactly is GAN?
This article is packed with valuable information, perfect for saving! At the end of the article, there is additional GAN resources for everyone to copy the link for learning and reference~ GAN resources

Main Application Goals of GAN:

Generative tasks (generation, reconstruction, super-resolution, style transfer, completion, upsampling, etc.)

The Core Idea of GAN:

Generative model G and discriminator D engage in generations of games

Generator: A generating network that produces images from input

Discriminator: A binary classification network that uses images generated by the generator as negative samples and real images as positive samples

Learn Discriminator D: Given G, generate images through G to create negative samples, and combine them with real images as positive samples to train D

Learn Generator G: Given D, train G to make D’s scoring of images generated by G as close to positive samples as possible

The training process of G and D alternates, and this adversarial process makes the images generated by G increasingly realistic, while D’s ability to

Leave a Comment