Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks.

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

Open Access

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

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

DOAJ Szczepanski

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

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

DOAJ

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

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

DOAJ Multiple Versions

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

DOAJ

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

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

DOAJ

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

Open Access

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

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

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

Multiple Versions

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

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

Preserved Fulltext

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

Preserved Fulltext

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

Preserved Fulltext

Adversarial Images for Variational Autoencoders [article]

Preserved Fulltext

Enhancing neural non-intrusive load monitoring with generative adversarial networks

Preserved Fulltext

Implicit Discriminator in Variational Autoencoder [article]

Preserved Fulltext

QCD or what?

Preserved Fulltext

Other Versions

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

Preserved Fulltext

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

Preserved Fulltext

Mixed-type data generation method based on generative adversarial networks

Preserved Fulltext

Generating Video From Images using GAN and CVAE

Preserved Fulltext

Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder

Preserved Fulltext

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

Preserved Fulltext

Deep clustering with fusion autoencoder [article]

Preserved Fulltext

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

Preserved Fulltext