29 datasets found

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a tunable GAN, called α-GAN, to generate samples from a distribution.

This study proposes CSI2Image, a novel channel-state-information (CSI)-to-image conversion method based on generative adversarial networks (GANs).

A new method for building open-ended vocabularies of primitive visual concepts represented in a GAN's latent space.

A novel deep-learning approach based on generative adversarial networks to perform super-resolution reconstruction of sparse measurements.

Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. However,...

Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. However,...

The authors used a simple benchmark where the data has a high-dimensional Gaussian distribution.

The dataset used in the paper is the W-space of StyleGAN2, which is a latent space of a generative adversarial network (GAN) model.

Generative Adversarial Networks (GANs) have a great performance in image generation, but they need a large scale of data to train the entire framework, and often result in...

The dataset used in the paper is a 2D mixture of 8 Gaussians evenly arranged in a circle. The generator has to search for 2D submanifolds in a 3D space.

Synthetic data, 2D mixture of Gaussian data, MNIST dataset, CIFAR-10 dataset

Generative adversarial nets (GANs) are a class of deep learning models that consist of two neural networks: a generator and a discriminator.

Generative adversarial networks (GANs) are powerful gen-erative models, but usually suffer from instability and generalization problem which may lead to poor generations.

The dataset used in the paper is a 2D submanifold mixture of seven Gaussians arranged in a circle and embedded in 3D space.

The dataset used in the paper is a synthetic dataset for testing the proposed Fake-As-Real GAN (FARGAN) method.

GANs trained on a dataset of GANs

The dataset used in the paper is a mixture of Gaussian tasks with 9 and 16 modes.

Generative Adversarial Networks (GANs) consist of two networks: a generator G(z) and a discriminator D(x). The discriminator is trying to distinguish real objects from objects...

The dataset used in the paper is a Generative Adversarial Networks (GANs) dataset, which includes various GANs architectures and their applications in mobile edge networks.

Font generation experiment using GlyphGAN, including legibility, diversity, and style consistency evaluation.