Variational Autoencoded Compositional Pattern Generative Adversarial Network for Handwritten Super Resolution Image Generation

Caren Güzel Turhan, H. Ş. Bilge
{"title":"Variational Autoencoded Compositional Pattern Generative Adversarial Network for Handwritten Super Resolution Image Generation","authors":"Caren Güzel Turhan, H. Ş. Bilge","doi":"10.1109/UBMK.2018.8566539","DOIUrl":null,"url":null,"abstract":"Since generative adversarial training has been decleared as one of the most exciting topics of the last 10 years by the pioneers, many researchers have focused on the Generative Adversarial Network (GAN) in their studies. On the otherhand, Variational Autoencoders (VAE) had gain autoencoders' popularity back. Due to some restrictions of GAN models and their lack of inference mechanism, hybrid models of GAN and VAE have emerged for image generation problem in nowadays. With the influence of these views and improvements, we have focused on addressing not only generating synthetic handwritten images but also their high-resolution version. For these tasks, Compositional Pattern Producing Networks (CPPN), VAE and GAN models are combined inspired by an existing model with some modification of its objective function. With this model, the idea behind the inspired study for generating high-resolution images are combined with the feature-wise reconstruction objective of a VAE/GAN hybrid model instead of pixel-like reconstruction approach of traditional VAE. For evaluating the model efficiency, our VAE/CPGAN model is compared with its basis models (GAN, VAE and VAE/GAN) and inspired model accoording to inception score. In this study, it is clearly seen that the proposed model is able to converge much faster than compared models for modeling the underlying distribution of handwritten image data.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/UBMK.2018.8566539","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Since generative adversarial training has been decleared as one of the most exciting topics of the last 10 years by the pioneers, many researchers have focused on the Generative Adversarial Network (GAN) in their studies. On the otherhand, Variational Autoencoders (VAE) had gain autoencoders' popularity back. Due to some restrictions of GAN models and their lack of inference mechanism, hybrid models of GAN and VAE have emerged for image generation problem in nowadays. With the influence of these views and improvements, we have focused on addressing not only generating synthetic handwritten images but also their high-resolution version. For these tasks, Compositional Pattern Producing Networks (CPPN), VAE and GAN models are combined inspired by an existing model with some modification of its objective function. With this model, the idea behind the inspired study for generating high-resolution images are combined with the feature-wise reconstruction objective of a VAE/GAN hybrid model instead of pixel-like reconstruction approach of traditional VAE. For evaluating the model efficiency, our VAE/CPGAN model is compared with its basis models (GAN, VAE and VAE/GAN) and inspired model accoording to inception score. In this study, it is clearly seen that the proposed model is able to converge much faster than compared models for modeling the underlying distribution of handwritten image data.
用于手写超分辨率图像生成的变分自编码组合模式生成对抗网络
由于生成对抗训练已被先驱们宣布为过去10年中最令人兴奋的主题之一,许多研究人员在他们的研究中关注了生成对抗网络(GAN)。另一方面,变分自编码器(VAE)重新赢得了自编码器的流行。由于GAN模型的局限性和缺乏推理机制,目前出现了GAN和VAE混合模型来解决图像生成问题。在这些观点和改进的影响下,我们不仅专注于生成合成的手写图像,还专注于它们的高分辨率版本。为了完成这些任务,组合模式生成网络(CPPN)、VAE和GAN模型在现有模型的启发下结合起来,并对其目标函数进行了一些修改。通过该模型,将生成高分辨率图像的灵感研究背后的思想与VAE/GAN混合模型的特征重建目标相结合,而不是传统VAE的类像素重建方法。为了评估模型的有效性,根据初始分数将我们的VAE/CPGAN模型与其基础模型(GAN、VAE和VAE/GAN)和启发模型进行了比较。在本研究中,可以清楚地看到,在对手写图像数据的底层分布进行建模时,所提出的模型能够比比较模型更快地收敛。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信