Results 41 to 50 of about 215,845 (322)
Poly-GAN: Multi-conditioned GAN for fashion synthesis [PDF]
Neurocomputing, 2020 We present Poly-GAN, a novel conditional GAN architecture that is motivated by Fashion Synthesis, an application where garments are automatically placed on images of human models at an arbitrary pose. Poly-GAN allows conditioning on multiple inputs and is suitable for many tasks, including image alignment, image stitching, and inpainting.
Andreas Savakis, Nilesh Pandey
openaire +3 more sources
DC-DC Converter Design Issues for High-Efficient DC Microgrid
Communications, 2019 In this article, the electrical properties, as well as the economic aspects of the modular and non-modular solution of the DC-DC photovoltaic converter for DC microgrid subsystem, are described.
Michal Frivaldsky, Jan Morgos
doaj +1 more source
Data Augmentation using Adversarial Networks for Tea Diseases Detection
Jurnal Elektronika dan Telekomunikasi, 2020 Deep learning technology has a better result when trained using an abundant amount of data. However, collecting such data is expensive and time consuming. On the other hand, limited data often be the inevitable condition. To increase the number of data,
R. Sandra Yuwana +5 more
doaj +1 more source
Integration of GaN analog building blocks on p-GaN wafers for GaN ICs
Journal of Semiconductors, 2021 Abstract We demonstrate the key module of comparators in GaN ICs, based on resistor-transistor logic (RTL) on E-mode wafers in this work. The fundamental inverters in the comparator consist of a p-GaN gate HEMT and a 2DEG resistor as the load.
Li, Xiangdong +8 more
openaire +4 more sources
Remote Sensing, 2020 Hyperspectral image analysis plays an important role in agriculture, mineral industry, and for military purposes. However, it is quite challenging when classifying high-dimensional hyperspectral data with few labeled samples.
Wenzhi Zhao +3 more
doaj +1 more source
Stylized Projected GAN: A Novel Architecture for Fast and Realistic Image Generation [PDF]
arXiv, 2023 Generative Adversarial Networks are used for generating the data using a generator and a discriminator, GANs usually produce high-quality images, but training GANs in an adversarial setting is a difficult task. GANs require high computation power and hyper-parameter regularization for converging. Projected GANs tackle the training difficulty of GANs by
arxiv
Selective Etching of GaN from AlGaN/GaN and AlN/GaN Structures [PDF]
MRS Internet Journal of Nitride Semiconductor Research, 2004 Thick GaN layers as well as AlGaN/GaN and AlN/GaN heterostructures grown by metalorganic vapor phase epitaxy have been photoelectrochemically (PEC) etched in various dilute electrolytes, and bandgap-selective etching has been demonstrated in heterostructures.
C. L. Reynolds +6 more
openaire +2 more sources
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 papers on generative modeling: https://github.com/zhoubolei/awesome-generative-modeling awesome gan-inversion papers: https://github.com/weihaox/awesome-gan ...
Weihao Xia +5 more
openaire +4 more sources
BiVi-GAN: Bivariate Vibration GAN
SensorsIn the domain of prognosis and health management (PHM) for rotating machinery, the criticality of ensuring equipment reliability cannot be overstated. With developments in artificial intelligence (AI) and deep learning, there have been numerous attempts to use those methodologies in PHM.
HoeJun Jeong +3 more
openaire +3 more sources
Diffusion-GAN: Training GANs with Diffusion
, 2022 Project homepage: https://github.com/Zhendong-Wang/Diffusion-GAN; ICLR 2023 camera ready ...
Wang, Zhendong +4 more
openaire +2 more sources