skylinemarketing/Generative-Adversarial-Networks-Roadmap

The Roadmap to Learn Generative Adversarial Networks (GANs)

GANs World Resources

Slack Group

Table of Contents

• Introduction
  • Motivation
    • What's the point of this open source project?
• Papers
  • Types and Models
    • Core: Generative Adversarial Networks (VanillaGAN)
    • Conditional Generative Adversarial Networks (CGAN)
    • Laplacian Pyramid of Adversarial Networks (LAPGAN)
    • Deep Convolutional Generative Adversarial Networks (DCGAN)
    • Adversarial Autoencoders (AAE)
    • Generative Recurrent Adversarial Networks (GRAN)
    • Information Maximizing Generative Adversarial Networks (InfoGan)
    • Bidirectional Generative Adversarial Networks (BiGan)
  • Applications
    • GANs Theory and Training
    • Image Synthesis
    • Image-to-image translation
    • Super-resolution
    • Text to Image
    • Image Editing
    • ETC
• Courses
• Books
• Tutorials
• Pull Request Process
• Final Note

Introduction

The purpose of this project is to introduce a shortcut to developers and researcher for finding useful resources about Generative Adversarial Networks.

Motivation

There are different motivations for this open source project.

What's the point of this open source project?

The organization of the resources is such that the user can easily find the things he/she is looking for. We divided the resources to a large number of categories that in the beginning one may have a headache!!! However, if someone knows what is being located, it is very easy to find the most related resources. Even if someone doesn't know what to look for, in the beginning, the list of resources have been provided.

Papers

This chapter is associated with the papers published associated with generative adversarial Networks.

Types and Models

Image by: Rouzbeh Asghari Shirvani

Core: Generative Adversarial Networks (VanillaGAN)

Title	Text	Software	Citation
Generative Adversarial Nets	Paper	Code	Rate 🌟 🌟 🌟 🌟 🌟
ENERGY-BASED GENERATIVE ADVERSARIAL NETWORK	Paper	Code	Rate 🌟 🌟 🌟 🌟
Which Training Methods for GANs do Actually Converge	Paper	Code	Rate 🌟 🌟

Conditional Generative Adversarial Networks (CGAN)

Title	Text	Software	Citation
Conditional generative adversarial nets	Paper	Code	Rate 🌟 🌟 🌟 🌟 🌟
Photo-realistic single image super-resolution using a GAN	Paper	Code	Rate 🌟 🌟 🌟 🌟
Image-to-Image Translation with Conditional Adversarial Networks	Paper	Code	Rate 🌟 🌟 🌟 🌟
Generative Visual Manipulation on the Natural Image Manifold	Paper	Code	Rate 🌟 🌟

Laplacian Pyramid of Adversarial Networks (LAPGAN)

Title	Text	Software	Citation
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks	Paper	Code	Rate 🌟 🌟 🌟 🌟 🌟

Deep Convolutional Generative Adversarial Networks (DCGAN)

Title	Text	Software	Citation
Deep Convolutional Generative Adversarial Networks	Paper	Code	Rate 🌟 🌟 🌟 🌟 🌟
Generative Adversarial Text to Image Synthesis	Paper	Code	Rate 🌟 🌟 🌟

Adversarial Autoencoders (AAE)

Title	Text	Software	Citation
Adversarial Autoencoders	Paper	Code	Rate 🌟 🌟 🌟 🌟 🌟

Generative Recurrent Adversarial Networks (GRAN)

Title	Text	Software	Citation
Generating images with recurrent adversarial networks	Paper	Code	Rate 🌟 🌟 🌟 🌟

Information Maximizing Generative Adversarial Networks (InfoGan)

Title	Text	Software	Citation
Infogan: Information maximizing GANs	Paper	Code	Rate 🌟 🌟 🌟 🌟 🌟

Bidirectional Generative Adversarial Networks (BiGan)

Title	Text	Software	Citation
Adversarial feature learning	Paper	Code	Rate 🌟 🌟 🌟 🌟 🌟

Applications

GANs Theory and Training

Title	Text		Software
Energy-based generative adversarial network	Paper		Code
Which Training Methods for GANs do actually Converge	Paper		Code
Improved Techniques for Training GANs	Paper		Code
Towards Principled Methods for Training Generative Adversarial Networks	Paper
Least Squares Generative Adversarial Networks	Paper		Code
Wasserstein GAN	Paper		Code
Improved Training of Wasserstein GANs	Paper		Code
Generalization and Equilibrium in Generative Adversarial Nets	Paper
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium	Paper		Code
Spectral Normalization for Generative Adversarial Networks	Paper		Code

Image Synthesis

Title	Text	Software
Generative Adversarial Text to Image Synthesis	Paper	Code
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space	Paper	Code
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks	Paper	Code
Progressive Growing of GANs for Improved Quality, Stability, and Variation	Paper	Code
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks	Paper	Code
Self-Attention Generative Adversarial Networks	Paper	Code
Large Scale GAN Training for High Fidelity Natural Image Synthesis	Paper

Image-to-image translation

Title	Text	Software
Image-to-image translation using conditional adversarial nets	Paper	Code
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks	Paper	Code
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks	Paper	Code
CoGAN: Coupled Generative Adversarial Networks	Paper	Code
Unsupervised Image-to-Image Translation Networks	Paper
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs	Paper
UNIT: UNsupervised Image-to-image Translation Networks	Paper	Code
Multimodal Unsupervised Image-to-Image Translation	Paper	Code

Super-resolution

Title	Text	Software
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network	Paper	Code
High-Quality Face Image Super-Resolution Using Conditional Generative Adversarial Networks	Paper
Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network	Paper	Code

Text to Image

Title	Text	Software
TAC-GAN – Text Conditioned Auxiliary Classifier Generative Adversarial Network	Paper	Code
Generative Adversarial Text to Image Synthesis	Paper	Code
Learning What and Where to Draw	Paper	Code

Image Editing

Title	Text	Software
Invertible Conditional GANs for image editing	Paper	Code
Image De-raining Using a Conditional Generative Adversarial Network	Paper	Code

ETC

Title	Text	Software
Generating multi-label discrete patient records using generative adversarial networks	Paper	Code
Adversarial Generation of Natural Language	Paper
Language Generation with Recurrent Generative Adversarial Networks without Pre-training	Paper	Code
Adversarial ranking for language generation	Paper	Code
Adversarial Training Methods for Semi-Supervised Text Classification	Paper	Code

Courses

• Deep Learning: GANs and Variational Autoencoders by Udemy: [Link]
• Differentiable Inference and Generative Models by the University of Toronto: [Link]
• Learning Generative Adversarial Networks by Udemy: [Link]

Books

• GANs in Action - Deep learning with Generative Adversarial Networks by manning Publications: [Link]

Tutorials

• GANs from Scratch 1: A deep introduction. With code in PyTorch and TensorFlow: [Link]
• Keep Calm and train a GAN. Pitfalls and Tips on training Generative Adversarial Networks: [Link]
• CVPR 2018 Tutorial on GANs: [Link]
• Introductory guide to Generative Adversarial Networks (GANs) and their promise!: [Link]
• Generative Adversarial Networks for beginners: [Link]
• Understanding and building Generative Adversarial Networks(GANs): [Link]

Pull Request Process

Please consider the following criterions in order to help us in a better way:

1. The pull request is mainly expected to be a link suggestion.
2. Please make sure your suggested resources are not obsolete or broken.
3. Ensure any install or build dependencies are removed before the end of the layer when doing a build and creating a pull request.
4. Add comments with details of changes to the interface, this includes new environment variables, exposed ports, useful file locations and container parameters.
5. You may merge the Pull Request in once you have the sign-off of at least one other developer, or if you do not have permission to do that, you may request the owner to merge it for you if you believe all checks are passed.

Final Note

We are looking forward to your kind feedback. Please help us to improve this open source project and make our work better. For contribution, please create a pull request and we will investigate it promptly. Once again, we appreciate your kind feedback and support.