Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models make them challenging to deploy widely practical applications. In particular, for real-time generation tasks, different devices require generators sizes due varying computing power. this paper, we introduce slimmable GANs (SlimGANs), which can flexibly switch wi...

Generative Adversarial Networks (GANs) is a novel class of deep generative models that has recently gained significant attention. GANs learn complex and high-dimensional distributions implicitly over images, audio, data. However, there exist major challenges in training GANs, i.e., mode collapse, non-convergence, instability, due to inappropriate design network architectre, use objective functi...

In recent years fully-parametric fast simulation methods based on generative models have been proposed for a variety of high-energy physics detectors. By their nature, the quality data-driven degrades in regions phase space where data are sparse. Since machine-learning hard to analyse from physical principles, commonly used testing procedures performed way and can't be reliably such regions. ou...

In this paper we investigate the problem of inducing a distribution over three-dimensional structures given twodimensional views of multiple objects taken from unknown viewpoints. Our approach called “projective generative adversarial networks” (PrGANs) trains a deep generative model of 3D shapes whose projections match the distributions of the input 2D views. The addition of a projection modul...

Traditional image steganography modifies the content of the image more or less, it is hard to resist the detection of image steganalysis tools. To address this problem, a novel method named generative coverless information hiding method based on generative adversarial networks is proposed in this paper. The main idea of the method is that the class label of generative adversarial networks is re...

We investigate Generative Adversarial Networks (GANs) to model one particular kind of image: frames from TV cartoons. Cartoons are particularly interesting because their visual appearance emphasizes the important semantic information about a scene while abstracting out the less important details, but each cartoon series has a distinctive artistic style that performs this abstraction in differen...

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesise novel, highdimensional data samples. New data samples are synthesised by passing latent samples, drawn from a chosen prior distribution, through the generative model. Once trained, the latent space exhibits interesting properties, that may be useful for down stream tasks such as classification or ret...

Generative grammarians have relied on introspective intuitions of well-formedness as their primary source of data. The overreliance on this one type of data and the unsystematic manner in which they are collected cast doubt on the empirical basis of a great deal of syntactic theorizing. These concerns are illustrated with examples and one more detailed case study, concerning the English verb-pa...

Building a voice conversion (VC) system from non-parallel speech corpora is challenging but highly valuable in real application scenarios. In most situations, the source and the target speakers do not repeat the same texts or they may even speak different languages. In this case, one possible, although indirect, solution is to build a generative model for speech. Generative models focus on expl...