Generative Adversarial Networks (GAN)


The generative network generates candidates while the discriminative network evaluates them. Typically, the generative network learns to map from a latent space to a data distribution of interest, while the discriminative network distinguishes candidates produced by the generator from the true data distribution. The generative network's training objective is to increase the error rate of the discriminative network.

Getting started

6 GAN Architectures You Really Should Know
Some of the most popular GAN architectures, particularly 6 architectures that you should know to have a diverse coverage on GANs.
generative-adversarial-networks survey tutorial article
PyTorch - GAN
PyTorch implementations of Generative Adversarial Networks.
generative-adversarial-networks pytorch began cyclegan

Tutorials

6 GAN Architectures You Really Should Know
Some of the most popular GAN architectures, particularly 6 architectures that you should know to have a diverse coverage on GANs.
generative-adversarial-networks survey tutorial article
GANSpace: Discovering Interpretable GAN Controls
This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis.
generative-adversarial-networks image-generation interpretability interpretable-gans
Big GANs Are Watching You
We demonstrate that object saliency masks for GAN-produced images can be obtained automatically with BigBiGAN.
generative-adversarial-networks unet object-saliency big-gan
Adversarial Latent Autoencoders
Introducing the Adversarial Latent Autoencoder (ALAE), a general architecture that can leverage recent improvements on GAN training procedures.
autoencoders generative-adversarial-networks latent-space disentanglement

Libraries

SimpleGAN
A Tensorflow-based framework to ease the training of generative models
computer-vision generative-adversarial-networks tensorflow deep-learning
Mimicry
A PyTorch library for the reproducibility of GAN research.
generative-adversarial-networks pytorch benchmarks reproducability
GAN Lab
An Interactive, Visual Experimentation Tool for Generative Adversarial Networks
interactive generative-adversarial-networks visualization neural-networks
PyTorch - GAN
PyTorch implementations of Generative Adversarial Networks.
generative-adversarial-networks pytorch began cyclegan

Research

GANSpace: Discovering Interpretable GAN Controls
This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis.
generative-adversarial-networks image-generation interpretability interpretable-gans
Big GANs Are Watching You
We demonstrate that object saliency masks for GAN-produced images can be obtained automatically with BigBiGAN.
generative-adversarial-networks unet object-saliency big-gan
Adversarial Latent Autoencoders
Introducing the Adversarial Latent Autoencoder (ALAE), a general architecture that can leverage recent improvements on GAN training procedures.
autoencoders generative-adversarial-networks latent-space disentanglement
Cycle Text-To-Image GAN with BERT
Image generation from their respective captions, building on state-of-the-art GAN architectures.
generative-adversarial-networks bert transformers image-to-text
AI-Art
PyTorch implementation of Neural Style Transfer, Pix2Pix, CycleGAN, and Deep Dream!
neural-style-transfer pix2pix cyclegan pytorch

Recent

NAG - Network for Adversary Generation [Pytorch]
Generative approach to model the manifold of perturbations that can cause CNN based classifiers to behave absurdly.
generative-adversarial-networks adversarial-attacks adversarial-learning arxiv:1712.03390
AI-Art
PyTorch implementation of Neural Style Transfer, Pix2Pix, CycleGAN, and Deep Dream!
neural-style-transfer pix2pix cyclegan pytorch
Deblending galaxy images using GAN's
The goal is to reconstruct the individual galaxy profiles where there is a line of sight overlap.
generative-adversarial-networks paper arxiv:1810.10098 dataset
Table of Contents
Share a resource
Share a resource you found useful for this specific topic.
Topic experts
Share