159,201 Hits in 3.8 sec

Generative Adversarial Networks [article]

Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
2014 arXiv   pre-print
There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples.  ...  We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative  ...  Adversarial models may also gain some statistical advantage from the generator network not being updated directly with data examples, but only with gradients flowing through the discriminator.  ... 
arXiv:1406.2661v1 fatcat:aohcfjejgbf4vjehuzcx257orq

Generating Adversarial Examples with Adversarial Networks [article]

Chaowei Xiao, Bo Li, Jun-Yan Zhu, Warren He, Mingyan Liu, Dawn Song
2019 arXiv   pre-print
In this paper, we propose AdvGAN to generate adversarial examples with generative adversarial networks (GANs), which can learn and approximate the distribution of original instances.  ...  Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs.  ...  Conclusion In this paper, we propose AdvGAN to generate adversarial examples using generative adversarial networks (GANs).  ... 
arXiv:1801.02610v5 fatcat:7wginnkytvar7fdp6j6xh6npiu

Generating Adversarial Examples with Adversarial Networks

Chaowei Xiao, Bo Li, Jun-yan Zhu, Warren He, Mingyan Liu, Dawn Song
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In this paper, we propose AdvGAN to generate adversarial exam- ples with generative adversarial networks (GANs), which can learn and approximate the distribution of original instances.  ...  Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs.  ...  RELATED WORK Here we review recent work on adversarial examples and generative adversarial networks.  ... 
doi:10.24963/ijcai.2018/543 dblp:conf/ijcai/XiaoLZHLS18 fatcat:v6wgdulyhffdhlesq74p444dve

Optimized Generative Adversarial Networks for Adversarial Sample Generation

Daniyal M. Alghazzawi, Syed Hamid Hasan, Surbhi Bhatia
2022 Computers Materials & Continua  
We are using Deep Convolutional Generative Adversarial Networks (DCGAN) to trick the malware classifier to believe it is a normal entity.  ...  Detecting the anomalous entity in real-time network traffic is a popular area of research in recent times.  ...  The generated adversarial examples are minimized by training a generative network.  ... 
doi:10.32604/cmc.2022.024613 fatcat:fxxlxr4atzb7fcokvsb7ja74tq

Deconstructing Generative Adversarial Networks [article]

Banghua Zhu, Jiantao Jiao, David Tse
2019 arXiv   pre-print
meaningful low-dimensional generator approximations when the real distribution is high-dimensional and corrupted by outliers. 2.  ...  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  ...  Recently, Generative Adversarial Networks (GANs) become a thriving unsupervised machine learning technique that has led to significant advances in various fields such as computer vision, natural language  ... 
arXiv:1901.09465v7 fatcat:6eop7iu52raxro2h5at5wa7mga

Controllable Generative Adversarial Network [article]

Minhyeok Lee, Junhee Seok
2019 arXiv   pre-print
Recently introduced generative adversarial network (GAN) has been shown numerous promising results to generate realistic samples.  ...  By separating a feature classifier from a discriminator, the generator of ControlGAN is designed to learn generating synthetic samples with the specific detailed features.  ...  Introduction Generative Adversarial Network (GAN) is a neural network structure, which has been introduced for generating realistic samples.  ... 
arXiv:1708.00598v5 fatcat:khdihuwg3nfszefq34qjjvjq7q

Targeted Speech Adversarial Example Generation with Generative Adversarial Network

Donghua Wang, Li Dong, Rangding Wang, Diqun Yan, Jie Wang
2020 IEEE Access  
GENERATIVE ADVERSARIAL NETWORK The generative adversarial network (GAN) was first proposed by Goodfellow et al. [11] .  ...  Our proposed method implants the target network into a generative adversarial network framework.  ... 
doi:10.1109/access.2020.3006130 fatcat:w7tksb7qujdifpilsd27776ory

Modular Generative Adversarial Networks [article]

Bo Zhao, Bo Chang, Zequn Jie, Leonid Sigal
2018 arXiv   pre-print
Inspired by recent work on module networks, this paper proposes ModularGAN for multi-domain image generation and image-to-image translation.  ...  This leads to ModularGAN's superior flexibility of generating (or translating to) an image in any desired domain.  ...  To achieve and formalize this incremental image generation process, we propose the modular generative adversarial network (ModularGAN).  ... 
arXiv:1804.03343v1 fatcat:dxhbgg3qprbw3oa34mzlhzv6my

Constrained Generative Adversarial Networks

Xiaopeng Chao, Jiangzhong Cao, Yuqin Lu, Qingyun Dai, Shangsong Liang
2021 IEEE Access  
INDEX TERMS Generative adversarial networks, Nash equilibrium, Lipschitz constraint.  ...  Generative Adversarial Networks (GANs) are a powerful subclass of generative models. Yet, how to effectively train them to reach Nash equilibrium is a challenge.  ...  LOSS FUNCTIONS FOR TRAINING GANs AND ITS VARIANTS Generative Adversarial Networks aim at training two networks, a generative network and an adversarial network, that compete against each other.  ... 
doi:10.1109/access.2021.3054822 fatcat:kj42bfzpdfej7n3ni2deh65pye

Coupled Generative Adversarial Networks [article]

Ming-Yu Liu, Oncel Tuzel
2016 arXiv   pre-print
We propose coupled generative adversarial network (CoGAN) for learning a joint distribution of multi-domain images.  ...  This is achieved by enforcing a weight-sharing constraint that limits the network capacity and favors a joint distribution solution over a product of marginal distributions one.  ...  Generative Adversarial Networks A GAN consists of a generative model and a discriminative model.  ... 
arXiv:1606.07536v2 fatcat:xn7d2hx45jhidf6mr2whyofhae

Triangle Generative Adversarial Networks [article]

Zhe Gan, Liqun Chen, Weiyao Wang, Yunchen Pu, Yizhe Zhang, Hao Liu, Chunyuan Li, Lawrence Carin
2017 arXiv   pre-print
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  ...  Δ-GAN consists of four neural networks, two generators and two discriminators.  ...  Model Generative Adversarial Networks (GANs) Generative Adversarial Networks (GANs) [1] consist of a generator G and a discriminator D that compete in a two-player minimax game, where the generator  ... 
arXiv:1709.06548v2 fatcat:hcuaf4mklrbyrdbfw3nye2wwwa

Slimmable Generative Adversarial Networks [article]

Liang Hou, Zehuan Yuan, Lei Huang, Huawei Shen, Xueqi Cheng, Changhu Wang
2021 arXiv   pre-print
Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes them challenging to deploy widely in practical applications.  ...  In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power.  ...  Preliminaries Generative Adversarial Networks Generative adversarial networks (GANs) (Goodfellow et al. 2014) are typically composed of a generator and a discriminator.  ... 
arXiv:2012.05660v3 fatcat:dnpkc5owprbizegvvrjbw3mrfm

Quantum generative adversarial networks

Pierre-Luc Dallaire-Demers, Nathan Killoran
2018 Physical Review A  
In this work and a companion paper, we extend adversarial training to the quantum domain and show how to construct generative adversarial networks using quantum circuits.  ...  Furthermore, we also show how to compute gradients -- a key element in generative adversarial network training -- using another quantum circuit.  ...  One of the most exciting recent developments in deep learning is generative adversarial networks (GANs) [4] .  ... 
doi:10.1103/physreva.98.012324 fatcat:6seiaw5ccjhpjcnmx4r5ukxnse

Stacked Generative Adversarial Networks

Xun Huang, Yixuan Li, Omid Poursaeed, John Hopcroft, Serge Belongie
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network  ...  A representation discriminator is introduced at each feature hierarchy to encourage the representation manifold of the generator to align with that of the bottomup discriminative network, leveraging the  ...  In Sec. 3.1 we briefly overview the framework of Generative Adversarial Networks. We then describe our proposal for Stacked Generative Adversarial Networks in Sec. 3.2.  ... 
doi:10.1109/cvpr.2017.202 dblp:conf/cvpr/HuangLPHB17 fatcat:cx7dp4srmnepfplnmemkofb2iu

Prescribed Generative Adversarial Networks [article]

Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei, Michalis K. Titsias
2019 arXiv   pre-print
Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limited in two ways.  ...  PresGANs add noise to the output of a density network and optimize an entropy-regularized adversarial loss.  ...  Fitting Prescribed Generative Adversarial Networks We fit PresGANs following the same adversarial procedure used in GANs.  ... 
arXiv:1910.04302v1 fatcat:6r5e2oma5jdzpihdob4chv25va
« Previous Showing results 1 — 15 out of 159,201 results