Results 21 to 30 of about 124,232 (320)

Generative Adversarial Networks: An Overview [PDF]

open access: yesIEEE Signal Processing Magazine, 2018
Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image ...
Antonia Creswell   +5 more
openaire   +6 more sources

Deconstructing Generative Adversarial Networks [PDF]

open access: yesIEEE Transactions on Information Theory, 2020
We deconstruct the performance of GANs into three components: 1. Formulation: we propose a perturbation view of the population target of GANs. Building on this interpretation, we show that GANs can be viewed as a generalization of the robust statistics framework, and propose a novel GAN architecture, termed as Cascade GANs, to provably recover ...
Banghua Zhu, Jiantao Jiao, David Tse
openaire   +2 more sources

Generative Adversarial Networks

open access: yes, 2023
Generative Adversarial Networks (GANs) are very popular frameworks for generating high-quality data, and are immensely used in both the academia and industry in many domains. Arguably, their most substantial impact has been in the area of computer vision, where they achieve state-of-the-art image generation.
Cohen, Gilad, Giryes, Raja
openaire   +2 more sources

Generating synthesized computed tomography from CBCT using a conditional generative adversarial network for head and neck cancer patients

open access: yesTechnology in Cancer Research & Treatment, 2022
Purpose: To overcome the imaging artifacts and Hounsfield unit inaccuracy limitations of cone-beam computed tomography, a conditional generative adversarial network is proposed to synthesize high-quality computed tomography-like images from cone-beam ...
Yun Zhang PhD   +6 more
doaj   +1 more source

Constrained Generative Adversarial Networks [PDF]

open access: yesIEEE Access, 2021
Generative Adversarial Networks (GANs) are a powerful subclass of generative models. Yet, how to effectively train them to reach Nash equilibrium is a challenge. A number of experiments have indicated that one possible solution is to bound the function space of the discriminator.
Xiaopeng Chao   +4 more
openaire   +3 more sources

Multi‐style Chinese art painting generation of flowers

open access: yesIET Image Processing, 2021
With the proposal and development of Generative Adversarial Networks, the great achievements in the field of image generation are made. Meanwhile, many works related to the generation of painting art have also been derived. However, due to the difficulty
Feifei Fu   +3 more
doaj   +1 more source

Regularized Generative Adversarial Network [PDF]

open access: yesSSRN Electronic Journal, 2021
18 pages. Comments are welcome!
Di Cerbo, Gabriele   +2 more
openaire   +2 more sources

A Review of GAN-Based Super-Resolution Reconstruction for Optical Remote Sensing Images

open access: yesRemote Sensing, 2023
High-resolution images have a wide range of applications in image compression, remote sensing, medical imaging, public safety, and other fields. The primary objective of super-resolution reconstruction of images is to reconstruct a given low-resolution ...
Xuan Wang   +3 more
doaj   +1 more source

A PRIMER ON GENERATIVE ADVERSARIAL NETWORKS

open access: yesInternational Journal of Innovative Research in Computer Science & Technology, 2020
Generative Adversarial Networks (GANs) is a type of deep neural network architecture that utilizes unsupervised machine learning to generate data. They were presented in 2014, in a paper by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. This paper will introduce the core components of GANs.
Jyotsna Sharma   +4 more
openaire   +2 more sources

Stacked Generative Adversarial Networks [PDF]

open access: yes2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
CVPR 2017, camera-ready ...
John E. Hopcroft   +4 more
openaire   +3 more sources

Home - About - Disclaimer - Privacy