Deep Generative Models for Image Generation: A Practical Comparison Between Variational Autoencoders and Generative Adversarial Networks

Autor:	Mohamed El-Kaddoury, Mohammed Majid Himmi, Abdelhak Mahmoudi
Rok vydání:	2019
Předmět:	Adversarial system Image generation Computer science business.industry Deep learning Supervised learning Unsupervised learning Point (geometry) Artificial intelligence business Generative grammar
Zdroj:	Mobile, Secure, and Programmable Networking ISBN: 9783030228842 MSPN
DOI:	10.1007/978-3-030-22885-9_1
Popis:	Deep Learning models can achieve impressive performance in supervised learning but not for unsupervised one. In image generation problem for example, we have no concrete target vector. Generative models have been proven useful for solving this kind of issues. In this paper, we will compare two types of generative models: Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). We apply those methods to different data sets to point out their differences and see their capabilities and limits as well. We find that, while VAEs are easier and faster to train, their results are in general more blurry than the images generated by GANs. These last are more realistic but noisy.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::7d06c047c13b93cd6abc7645f07a6834 https://doi.org/10.1007/978-3-030-22885-9_1 Zobrazit plný text záznamu