Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

19 Nov 2015132 code implementations

In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications.

CONDITIONAL IMAGE GENERATION UNSUPERVISED REPRESENTATION LEARNING

Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

CVPR 2017 4 code implementations

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks.

UNSUPERVISED DOMAIN ADAPTATION

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

CVPR 2017 54 code implementations

The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.

IMAGE SUPER-RESOLUTION

A Style-Based Generator Architecture for Generative Adversarial Networks

CVPR 2019 29 code implementations

We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.

IMAGE GENERATION

Self-Attention Generative Adversarial Networks

arXiv 2018 32 code implementations

In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.

CONDITIONAL IMAGE GENERATION

Generative Adversarial Networks

10 Jun 201479 code implementations

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.

Coupled Generative Adversarial Networks

NeurIPS 2016 3 code implementations

We propose coupled generative adversarial network (CoGAN) for learning a joint distribution of multi-domain images.

DOMAIN ADAPTATION IMAGE-TO-IMAGE TRANSLATION

Boundary-Seeking Generative Adversarial Networks

27 Feb 20173 code implementations

We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.

SCENE UNDERSTANDING TEXT GENERATION

Least Squares Generative Adversarial Networks

ICCV 2017 9 code implementations

To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator.

Semi-Supervised Learning with Generative Adversarial Networks

5 Jun 20163 code implementations

We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels.