Multi-adversarial Variational Autoencoder Networks

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,...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) s. 777 - 782
Hlavní autori: Imran, Abdullah-Al-Zubaer, Terzopoulos, Demetri
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.12.2019
Predmet:
Computational modeling
Data models
Deep-generative-models
Gallium nitride
GANs
Generators
Image generation
image-classification
semi-supervised-learning
Supervised learning
Training
VAEs
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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.
DOI:10.1109/ICMLA.2019.00137