Results 31 to 40 of about 26,076 (260)

Controllable Generative Adversarial Network [PDF]

IEEE Access, 2019
A fully revised version of this paper is published in IEEE Access.
Minhyeok Lee, Junhee Seok
openaire   +3 more sources

Super‐resolution with adversarial loss on the feature maps of the generated high‐resolution image

Electronics Letters, 2022
Recent studies on image super‐resolution make use of Generative Adversarial Networks to generate the high‐resolution image counterpart of the low‐resolution input. However, while being able to generate sharp high‐resolution images, Generative Adversarial
I. Imanuel, S. Lee
doaj   +1 more source

Variational Generative Adversarial Networks for Preventing Mode Collapse [PDF]

هوش محاسباتی در مهندسی برق, 2022
Generative models try to obtain a probability distribution that is similar to that of observed data. Two different solutions have been proposed in this regard in recent years: one is to minimize the divergence (distance) between the two distributions by ...
Mehdi Jamaseb Khollari, Vali Derhami, Mehdi Yazdian Dehkordi   +2 more
doaj   +1 more source

Semi-supervised Learning on Graphs Using Adversarial Training with Generated Sample [PDF]

Jisuanji kexue yu tansuo, 2023
Given a graph composed of a small number of labeled nodes and a large number of unlabeled nodes, semi-supervised learning on graphs aims to assign labels for the unlabeled nodes.
WANG Cong, WANG Jie, LIU Quanming, LIANG Jiye
doaj   +1 more source

Dairy Goat Image Generation Based on Improved-Self-Attention Generative Adversarial Networks

IEEE Access, 2020
The lack of long-range dependence in convolutional neural networks causes weaker performance in generative adversarial networks(GANs) with regard to generating image details. The self-attention generative adversarial network(SAGAN) use the self-attention
Huan Li, Jinglei Tang
doaj   +1 more source

Structured Generative Adversarial Networks

CoRR, 2017
We study the problem of conditional generative modeling based on designated semantics or structures. Existing models that build conditional generators either require massive labeled instances as supervision or are unable to accurately control the semantics of generated samples.
Zhijie Deng, Hao Zhang 0025, Xiaodan Liang, Luona Yang, Shizhen Xu, Jun Zhu 0001, Eric P. Xing   +6 more
openaire   +3 more sources

Lung image segmentation via generative adversarial networks

Frontiers in Physiology
IntroductionLung image segmentation plays an important role in computer-aid pulmonary disease diagnosis and treatment.MethodsThis paper explores the lung CT image segmentation method by generative adversarial networks.
Jiaxin Cai, Hongfeng Zhu, Siyu Liu, Yang Qi, Rongshang Chen   +4 more
doaj   +1 more source

Triangle Generative Adversarial Networks

CoRR, 2017
A Triangle Generative Adversarial Network ($Δ$-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples.
Zhe Gan, Liqun Chen 0001, Weiyao Wang 0002, Yunchen Pu, Yizhe Zhang 0002, Hao Liu 0015, Chunyuan Li, Lawrence Carin   +7 more
openaire   +3 more sources

Modular Generative Adversarial Networks [PDF]

, 2018
Existing methods for multi-domain image-to-image translation (or generation) attempt to directly map an input image (or a random vector) to an image in one of the output domains. However, most existing methods have limited scalability and robustness, since they require building independent models for each pair of domains in question.
Bo Zhao 0032, Bo Chang 0002, Zequn Jie, Leonid Sigal   +3 more
openaire   +2 more sources

Generative Adversarial Optical Networks Using Diffractive Layers for Digit and Action Generation

Photonics
Within the traditional electronic neural network framework, Generative Adversarial Networks (GANs) have achieved extensive applications across multiple domains, including image synthesis, style transfer and data augmentation.
Pei Hu, Tengyu Cui, Yuanyuan Zhang, Shuai Feng   +3 more
doaj   +1 more source