Multi-adversarial variational autoencoder networks

Abdullah Al Zubaer Imran; Demetri Terzopoulos

doi:10.1109/ICMLA.2019.00137

Multi-adversarial variational autoencoder networks

Abdullah Al Zubaer Imran, Demetri Terzopoulos

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform unsupervised clustering or semi-supervised classification of images. Combining the power of these two generative models, we introduce a novel network architecture, Multi-Adversarial Variational autoEncoder Networks (MAVENs), which incorporate an ensemble of discriminators in a combined VAE-GAN network, with simultaneous adversarial learning and variational inference. We apply MAVENs to the generation of synthetic images and propose a new distribution measure to evaluate the quality of the generated images. Our experimental results using the computer vision datasets SVHN and CIFAR-10 demonstrate competitive performance against state-of-the-art semi-supervised models both in image generation and classification tasks.

Original language	English
Title of host publication	Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
Editors	M. Arif Wani, Taghi M. Khoshgoftaar, Dingding Wang, Huanjing Wang, Naeem Seliya
Pages	777-782
Number of pages	6
ISBN (Electronic)	9781728145495
DOIs	https://doi.org/10.1109/ICMLA.2019.00137
State	Published - Dec 2019
Event	18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 - Boca Raton, United States Duration: Dec 16 2019 → Dec 19 2019

Publication series

Name	Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

Conference

Conference	18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
Country/Territory	United States
City	Boca Raton
Period	12/16/19 → 12/19/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

-GANs
-VAEs
-image-classification
-image-generation
-semi-supervised-learning
Deep-generative-models

ASJC Scopus subject areas

Strategy and Management
Artificial Intelligence
Computer Science Applications
Decision Sciences (miscellaneous)
Signal Processing
Media Technology

Access to Document

10.1109/ICMLA.2019.00137

Cite this

Imran, A. A. Z., & Terzopoulos, D. (2019). Multi-adversarial variational autoencoder networks. In M. A. Wani, T. M. Khoshgoftaar, D. Wang, H. Wang, & N. Seliya (Eds.), Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 (pp. 777-782). Article 8999307 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019). https://doi.org/10.1109/ICMLA.2019.00137

Imran, Abdullah Al Zubaer ; Terzopoulos, Demetri. / Multi-adversarial variational autoencoder networks. Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. editor / M. Arif Wani ; Taghi M. Khoshgoftaar ; Dingding Wang ; Huanjing Wang ; Naeem Seliya. 2019. pp. 777-782 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019).

@inproceedings{e55b74c48d5043dba821cab083d4b956,

title = "Multi-adversarial variational autoencoder networks",

abstract = "The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform unsupervised clustering or semi-supervised classification of images. Combining the power of these two generative models, we introduce a novel network architecture, Multi-Adversarial Variational autoEncoder Networks (MAVENs), which incorporate an ensemble of discriminators in a combined VAE-GAN network, with simultaneous adversarial learning and variational inference. We apply MAVENs to the generation of synthetic images and propose a new distribution measure to evaluate the quality of the generated images. Our experimental results using the computer vision datasets SVHN and CIFAR-10 demonstrate competitive performance against state-of-the-art semi-supervised models both in image generation and classification tasks.",

keywords = "-GANs, -VAEs, -image-classification, -image-generation, -semi-supervised-learning, Deep-generative-models",

author = "Imran, {Abdullah Al Zubaer} and Demetri Terzopoulos",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 ; Conference date: 16-12-2019 Through 19-12-2019",

year = "2019",

month = dec,

doi = "10.1109/ICMLA.2019.00137",

language = "English",

series = "Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019",

pages = "777--782",

editor = "Wani, {M. Arif} and Khoshgoftaar, {Taghi M.} and Dingding Wang and Huanjing Wang and Naeem Seliya",

booktitle = "Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019",

}

Imran, AAZ & Terzopoulos, D 2019, Multi-adversarial variational autoencoder networks. in MA Wani, TM Khoshgoftaar, D Wang, H Wang & N Seliya (eds), Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019., 8999307, Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019, pp. 777-782, 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019, Boca Raton, United States, 12/16/19. https://doi.org/10.1109/ICMLA.2019.00137

Multi-adversarial variational autoencoder networks. / Imran, Abdullah Al Zubaer; Terzopoulos, Demetri.
Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. ed. / M. Arif Wani; Taghi M. Khoshgoftaar; Dingding Wang; Huanjing Wang; Naeem Seliya. 2019. p. 777-782 8999307 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-adversarial variational autoencoder networks

AU - Imran, Abdullah Al Zubaer

AU - Terzopoulos, Demetri

PY - 2019/12

Y1 - 2019/12

N2 - The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform unsupervised clustering or semi-supervised classification of images. Combining the power of these two generative models, we introduce a novel network architecture, Multi-Adversarial Variational autoEncoder Networks (MAVENs), which incorporate an ensemble of discriminators in a combined VAE-GAN network, with simultaneous adversarial learning and variational inference. We apply MAVENs to the generation of synthetic images and propose a new distribution measure to evaluate the quality of the generated images. Our experimental results using the computer vision datasets SVHN and CIFAR-10 demonstrate competitive performance against state-of-the-art semi-supervised models both in image generation and classification tasks.

AB - The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform unsupervised clustering or semi-supervised classification of images. Combining the power of these two generative models, we introduce a novel network architecture, Multi-Adversarial Variational autoEncoder Networks (MAVENs), which incorporate an ensemble of discriminators in a combined VAE-GAN network, with simultaneous adversarial learning and variational inference. We apply MAVENs to the generation of synthetic images and propose a new distribution measure to evaluate the quality of the generated images. Our experimental results using the computer vision datasets SVHN and CIFAR-10 demonstrate competitive performance against state-of-the-art semi-supervised models both in image generation and classification tasks.

KW - -GANs

KW - -VAEs

KW - -image-classification

KW - -image-generation

KW - -semi-supervised-learning

KW - Deep-generative-models

UR - http://www.scopus.com/inward/record.url?scp=85080885214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85080885214&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2019.00137

DO - 10.1109/ICMLA.2019.00137

M3 - Conference contribution

AN - SCOPUS:85080885214

T3 - Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

SP - 777

EP - 782

BT - Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

A2 - Wani, M. Arif

A2 - Khoshgoftaar, Taghi M.

A2 - Wang, Dingding

A2 - Wang, Huanjing

A2 - Seliya, Naeem

T2 - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

Y2 - 16 December 2019 through 19 December 2019

ER -

Imran AAZ, Terzopoulos D. Multi-adversarial variational autoencoder networks. In Wani MA, Khoshgoftaar TM, Wang D, Wang H, Seliya N, editors, Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. 2019. p. 777-782. 8999307. (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019). doi: 10.1109/ICMLA.2019.00137

Multi-adversarial variational autoencoder networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this