Filters








2,585 Hits in 7.3 sec

Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks [article]

Yuchong Yao, Xiaohui Wangr, Yuanbang Ma, Han Fang, Jiaying Wei, Liyuan Chen, Ali Anaissi, Ali Braytee
2022 arXiv   pre-print
In this work, we propose a novel Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks (CAPGAN) as an augmentation tool to generate realistic synthetic images  ...  In particular, we utilize a conditional convolutional variational autoencoder with supervised and balanced pre-training for the GAN initialization and training with gradient penalty.  ...  To this end, we propose a new framework, namely, Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks (CAPGAN).  ... 
arXiv:2201.04809v1 fatcat:lbg4zv75pjeqljhuxsmvnsfby4

Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder [article]

Hyungrok Ham, Tae Joon Jun, Daeyoung Kim
2020 arXiv   pre-print
We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE).  ...  Furthermore, we balance between the generator and the discriminator at early epochs and thus maintain the stabilized training of GANs.  ...  Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder CIFAR-10 For the CIFAR-10 dataset, we used 32× 32 image size and 4 × 4 downsampled images  ... 
arXiv:2002.02112v1 fatcat:yecfoe43lvdtrjh3pwfolnzbcu

A survey on generative adversarial networks for imbalance problems in computer vision tasks

Vignesh Sampath, Iñaki Maurtua, Juan José Aguilar Martín, Aitor Gutierrez
2021 Journal of Big Data  
In recent years, Generative Adversarial Neural Networks (GANs) have gained immense attention by researchers across a variety of application domains due to their capability to model complex real-world image  ...  It is particularly important that GANs can not only be used to generate synthetic images, but also its fascinating adversarial learning idea showed good potential in restoring balance in imbalanced datasets  ...  Acknowledgements The authors would like to thank the anonymous reviewers for their valuable comments and suggestions on the paper.  ... 
doi:10.1186/s40537-021-00414-0 pmid:33552840 pmcid:PMC7845583 fatcat:g3p6hbjuj5c5vbe23ms4g6ed6q

Adversarial Images for Variational Autoencoders [article]

Pedro Tabacof, Julia Tavares, Eduardo Valle
2016 arXiv   pre-print
We investigate adversarial attacks for autoencoders. We propose a procedure that distorts the input image to mislead the autoencoder in reconstructing a completely different target image.  ...  Finally, we show that the usual adversarial attack for classifiers, while being much easier, also presents a direct proportion between distortion on the input, and misdirection on the output.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.  ... 
arXiv:1612.00155v1 fatcat:esfo5uumq5h4ph6zrc5m6a7wvu

Enhancing neural non-intrusive load monitoring with generative adversarial networks

Kaibin Bao, Kanan Ibrahimov, Martin Wagner, Hartmut Schmeck
2018 Energy Informatics  
We propose to enhance Neural NILM approaches with appliance load sequence generators trained with a Generative Adversarial Network to mitigate the described problem.  ...  The preliminary results of our experiments with Generative Adversarial Networks show the potential of the approach, albeit there is no strong evidence yet that this approach outperforms the examined end-to-end-trained  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Published: 10 October 2018  ... 
doi:10.1186/s42162-018-0038-y fatcat:hzimkxcwmrcapivejiwjbdvw5i

Implicit Discriminator in Variational Autoencoder [article]

Prateek Munjal, Akanksha Paul, Narayanan C. Krishnan
2019 arXiv   pre-print
Recently generative models have focused on combining the advantages of variational autoencoders (VAE) and generative adversarial networks (GAN) for good reconstruction and generative abilities.  ...  In this work we introduce a novel hybrid architecture, Implicit Discriminator in Variational Autoencoder (IDVAE), that combines a VAE and a GAN, which does not need an explicit discriminator network.  ...  Introduction Deep Variational Autoencoders(VAE [15] ) and Generative Adversarial Networks(GAN [12] ) are two recently used approaches in the generative modeling world.  ... 
arXiv:1909.13062v1 fatcat:kmx5uuggnvci3kq6qvhhxsb3re

QCD or what?

Theo Heimel, Gregor Kasieczka, Tilman Plehn, Jennifer Thompson
2019 SciPost Physics  
Such an adversarial autoencoder allows for a general and at the same time easily controllable search for new physics.  ...  Autoencoder networks, trained only on QCD jets, can be used to search for anomalies in jet-substructure.  ...  We are grateful to Michel Luchmann for help with the improved image pre-processing.  ... 
doi:10.21468/scipostphys.6.3.030 fatcat:m7yrqkxnozhbdjetu5r7ulmq74

Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning

Junghoon Hah, Woojin Lee, Jaewook Lee, Saerom Park
2018 Computational Intelligence and Neuroscience  
We also train our model with proportional control theory to keep the equilibrium between the discriminator and the generator balanced, and as a result, our generative adversarial network can mitigate the  ...  This paper describes a new image generation algorithm based on generative adversarial network.  ...  Computational Intelligence and Neuroscience We trained an autoencoder network for the discriminator loss L D , a generator network for the generator loss L G , where L Q regularizes the generator not to  ... 
doi:10.1155/2018/6465949 pmid:30416519 pmcid:PMC6207896 dblp:journals/cin/HahLLP18 fatcat:hhptwms3k5hnxmvpxl4ltv67hq

A Generative Model based Adversarial Security of Deep Learning and Linear Classifier Models [article]

erhat Ozgur Catak and Samed Sivaslioglu and Kevser Sahinbas
2020 arXiv   pre-print
In this paper, we have proposed a mitigation method for adversarial attacks against machine learning models with an autoencoder model that is one of the generative ones.  ...  The main idea behind adversarial attacks against machine learning models is to produce erroneous results by manipulating trained models.  ...  They are associated with Generative Adversarial Networks due to their architectural similarity. In summary, variational autoencoders are also generative models.  ... 
arXiv:2010.08546v1 fatcat:trqowc5b5jbnvaqvgafyiui76m

Mixed-type data generation method based on generative adversarial networks

Ning Wei, Longzhi Wang, Guanhua Chen, Yirong Wu, Shunfa Sun, Peng Chen
2022 EURASIP Journal on Wireless Communications and Networking  
The model first pre-trains the autoencoder which maps given dataset into a low-dimensional continuous space.  ...  In this paper, a mixed-type data generation model based on generative adversarial networks is proposed to synthesize fake data that have the same distribution with the real data, so as to supplement the  ...  Acknowledgements The authors thank the anonymous reviewers and editors for their efforts in valuable comments and suggestions. Author Contributions NW and PC conceived and designed the study.  ... 
doi:10.1186/s13638-022-02105-7 fatcat:35oyfahxufeo3ejvsckt6yz73m

Generating Video From Images using GAN and CVAE

2020 International journal of recent technology and engineering  
which we propose a conditional variational autoencoder as a solution for this issue.  ...  We likewise propose another structure for assessing generative models through an adversarial procedure, wherein we simultaneously train two models, a generative model G that catches the information appropriation  ...  Conditional Variational Autoencoder (CVAE): A variational autoencoder (VAE) encodes a few data (for this situation a video) as a Gaussian appropriation, for example, a vector of means and standard deviations  ... 
doi:10.35940/ijrte.e6425.018520 fatcat:xjliqnu6lvhftawfrxux5pv4bq

Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder

Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Yui-Lam Chan
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We come up with a conditional variational autoencoder to encode the reference for dense feature vector which can then be transferred to the decoder for target image denoising.  ...  In this paper, we revisit the classic example based image super-resolution approaches and come up with a novel generative model for perceptual image super-resolution.  ...  This is also the first work on combining Variational AutoEncoder and Generative Adversarial Network for image super-resolution. 3.  ... 
doi:10.1109/cvprw50498.2020.00229 dblp:conf/cvpr/LiuSWLCC20 fatcat:pefpfnflxrcw5jutze5iphey4u

Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder [article]

Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Yui-Lam Chan
2020 arXiv   pre-print
We come up with a conditional variational autoencoder to encode the reference for dense feature vector which can then be transferred to the decoder for target image denoising.  ...  In this paper, we revisit the classic example based image super-resolution approaches and come up with a novel generative model for perceptual image super-resolution.  ...  This is also the first work on combining Variational AutoEncoder and Generative Adversarial Network for image super-resolution. 3.  ... 
arXiv:2004.12811v1 fatcat:iwrvcyfg4jamjijp3qv2j2eoi4

Deep clustering with fusion autoencoder [article]

Shuai Chang
2022 arXiv   pre-print
Specifically, the generative adversarial network and VAE are coalesced into a new autoencoder called fusion autoencoder (FAE) for discerning more discriminative representation that benefits the downstream  ...  Nowadays, a generative model named variational autoencoder (VAE) has got wide acceptance in DC studies.  ...  Variational autoencoder and generative adversarial network Variational AutoEncoder (VAE) can be viewed as two independently parametrized models: the recognition model and the generative model, a.k.a the  ... 
arXiv:2201.04727v2 fatcat:glfdqqyfjvdpvor7f3tslegjqe

Face-to-Music Translation Using a Distance-Preserving Generative Adversarial Network with an Auxiliary Discriminator [article]

Chelhwon Kim, Andrew Port, Mitesh Patel
2020 arXiv   pre-print
In this work, we propose a distance-preserving generative adversarial model to translate images of human faces into an audio domain.  ...  Further, we discover that the distance preservation constraint in the generative adversarial model leads to reduced diversity in the translated audio samples, and propose the use of an auxiliary discriminator  ...  As a result, total 60788 musical notes of the train split set defined in the NSynth dataset were used to train our models.  ... 
arXiv:2006.13469v1 fatcat:2wnvlc62vnegzljkgzskawfkx4
« Previous Showing results 1 — 15 out of 2,585 results