Results 11 to 20 of about 215,845 (322)
arXiv, 2019 Generative Adversarial Networks (GANs) have become a dominant class of generative models. In recent years, GAN variants have yielded especially impressive results in the synthesis of a variety of forms of data. Examples include compelling natural and artistic images, textures, musical sequences, and 3D object files.
arxiv +4 more sources
GAN-Control: Explicitly Controllable GANs [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 We present a framework for training GANs with explicit control over generated images. We are able to control the generated image by settings exact attributes such as age, pose, expression, etc. Most approaches for editing GAN-generated images achieve partial control by leveraging the latent space disentanglement properties, obtained implicitly after ...
Shoshan, Alon +3 more
openaire +2 more sources
IEEE Transactions on Neural Networks and Learning Systems, 2023 In this paper, we propose a novel loss function for training Generative Adversarial Networks (GANs) aiming towards deeper theoretical understanding as well as improved stability and performance for the underlying optimization problem. The new loss function is based on cumulant generating functions giving rise to \emph{Cumulant GAN}.
Yannis Pantazis +4 more
openaire +3 more sources
On the effect of N-GaN/P-GaN/N-GaN/P-GaN/N-GaN built-in junctions in the n-GaN layer for InGaN/GaN light-emitting diodes [PDF]
Optics Express, 2014 N-GaN/P-GaN/N-GaN/P-GaN/N-GaN (NPNPN-GaN) junctions embedded between the n-GaN region and multiple quantum wells (MQWs) are systematically studied both experimentally and theoretically to increase the performance of InGaN/GaN light emitting diodes (LEDs) in this work.
Kyaw, Zabu +12 more
openaire +6 more sources
H-GAN: the power of GANs in your Hands [PDF]
2021 International Joint Conference on Neural Networks (IJCNN), 2021 Paper accepted at The International Joint Conference on Neural Networks (IJCNN ...
Giorgos Karvounas +9 more
openaire +2 more sources
Improved InGaN/GaN light-emitting diodes with a p-GaN/n-GaN/p-GaN/n-GaN/p-GaN current-spreading layer [PDF]
Optics Express, 2013 This work reports both experimental and theoretical studies on the InGaN/GaN light-emitting diodes (LEDs) with optical output power and external quantum efficiency (EQE) levels substantially enhanced by incorporating p-GaN/n-GaN/p-GaN/n-GaN/p-GaN (PNPNP-GaN) current spreading layers in p-GaN.
Zhang, Z.-H. +9 more
openaire +5 more sources
Polarization effects in AlGaN/GaN and GaN/AlGaN/GaN heterostructures [PDF]
Journal of Applied Physics, 2003 The influence of AlGaN and GaN cap layer thickness on Hall sheet carrier density and mobility was investigated for Al0.32Ga0.68N/GaN and GaN/Al0.32Ga0.68N/GaN heterostructures deposited on sapphire substrates. The sheet carrier density was found to increase and saturate with the AlGaN layer thickness, while for the GaN-capped structures it decreased ...
Heikman, S +5 more
openaire +2 more sources
Growth of GaN on porous SiC and GaN substrates [PDF]
Journal of Electronic Materials, 2003 GaN films were grown on porous SiC and GaN templates using both plasma-assisted molecular beam epitaxy (PAMBE) and metal-organic chemical vapor deposition (MOCVD) to evaluate possible advantage of epitaxy on a porous substrate. For the growth of GaN on porous SiC by PAMBE, transmission electron microscopy (TEM) observations indicate that the exposed ...
Ashutosh Sagar +8 more
openaire +3 more sources
Cubic GaN and InGaN/GaN quantum wells
Applied Physics Reviews, 2022 LEDs based on hexagonal InGaN/GaN quantum wells are dominant technology for many lighting applications. However, their luminous efficacy for green and amber emission and at high drive currents remains limited. Growing quantum wells instead in the cubic phase is a promising alternative because, compared to hexagonal GaN, it benefits from a reduced ...
Binks, DJ +3 more
openaire +2 more sources
Deep Fake Image Detection Based on Pairwise Learning
Applied Sciences, 2020 Generative adversarial networks (GANs) can be used to generate a photo-realistic image from a low-dimension random noise. Such a synthesized (fake) image with inappropriate content can be used on social media networks, which can cause severe problems ...
Chih-Chung Hsu +2 more
doaj +1 more source