Image to Image Translation Networks using Perceptual Adversarial Loss Function

Saleh Altakrouri, S. Usman, N. Ahmad, Taghreed Justinia, N. Noor
{"title":"Image to Image Translation Networks using Perceptual Adversarial Loss Function","authors":"Saleh Altakrouri, S. Usman, N. Ahmad, Taghreed Justinia, N. Noor","doi":"10.1109/ICSIPA52582.2021.9576815","DOIUrl":null,"url":null,"abstract":"Image to image translation based on deep learning models is a subject of immense importance in the disciplines of Artificial Intelligence (AI) and Computer Vision (CV). A variety of traditional tasks such as image colorization, image denoising and image inpainting, are categorized as typical paired image translation tasks. In computer vision, super-resolution regeneration is particularly important field. We proposed an improved algorithm to mitigate the issues that arises during the reconstruction using super resolution based on generative adversarial network. It is difficult to train in reconstruction of results. The generated images and the corresponding ground-truth images should share the same fundamental structure in order to output the required resultant images. The shared basic structure between the input and the corresponding output image is not as optimal as assumed for paired image translation tasks, which can greatly impact the generating model performance. The traditional GAN based model used in image-to-image translation tasks used a pre-trained classification network. The pre-trained networks perform well on the classification tasks compared to image translation tasks because they were trained on features that contribute to better classification. We proposed the perceptual loss based efficient net Generative Adversarial Network (PL-E-GAN) for super resolution tasks. Unlike other state of the art image translation models, the PL-E-GAN offers a generic architecture for image super-resolution tasks. PL-E-GAN is constituted of two convolutional neural networks (CNNs) that are the Generative network and Discriminator network Gn and Dn, respectively. PL-E-GAN employed both the generative adversarial loss and perceptual adversarial loss as objective function to the network. The integration of these loss function undergoes an adversarial training and both the networks Gn and Dn trains alternatively. The feasibility and benefits of the PL-E-GAN over several image translation models are shown in studies and tested on many image-to-image translation tasks","PeriodicalId":326688,"journal":{"name":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSIPA52582.2021.9576815","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Image to image translation based on deep learning models is a subject of immense importance in the disciplines of Artificial Intelligence (AI) and Computer Vision (CV). A variety of traditional tasks such as image colorization, image denoising and image inpainting, are categorized as typical paired image translation tasks. In computer vision, super-resolution regeneration is particularly important field. We proposed an improved algorithm to mitigate the issues that arises during the reconstruction using super resolution based on generative adversarial network. It is difficult to train in reconstruction of results. The generated images and the corresponding ground-truth images should share the same fundamental structure in order to output the required resultant images. The shared basic structure between the input and the corresponding output image is not as optimal as assumed for paired image translation tasks, which can greatly impact the generating model performance. The traditional GAN based model used in image-to-image translation tasks used a pre-trained classification network. The pre-trained networks perform well on the classification tasks compared to image translation tasks because they were trained on features that contribute to better classification. We proposed the perceptual loss based efficient net Generative Adversarial Network (PL-E-GAN) for super resolution tasks. Unlike other state of the art image translation models, the PL-E-GAN offers a generic architecture for image super-resolution tasks. PL-E-GAN is constituted of two convolutional neural networks (CNNs) that are the Generative network and Discriminator network Gn and Dn, respectively. PL-E-GAN employed both the generative adversarial loss and perceptual adversarial loss as objective function to the network. The integration of these loss function undergoes an adversarial training and both the networks Gn and Dn trains alternatively. The feasibility and benefits of the PL-E-GAN over several image translation models are shown in studies and tested on many image-to-image translation tasks
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于感知对抗损失函数的图像到图像翻译网络
基于深度学习模型的图像到图像翻译是人工智能(AI)和计算机视觉(CV)学科中非常重要的课题。各种传统的任务,如图像着色、图像去噪和图像上绘,被归类为典型的成对图像翻译任务。在计算机视觉中,超分辨率再生是一个特别重要的领域。我们提出了一种基于生成对抗网络的超分辨率重建算法,以缓解重建过程中出现的问题。结果的重建训练是困难的。生成的图像和相应的真地图像应具有相同的基本结构,以便输出所需的合成图像。对于配对图像转换任务,输入和相应输出图像之间的共享基本结构并不像假设的那么理想,这将极大地影响生成模型的性能。传统的基于GAN的模型用于图像到图像的翻译任务,使用预训练的分类网络。与图像翻译任务相比,预训练的网络在分类任务上表现良好,因为它们是在有助于更好分类的特征上进行训练的。针对超分辨率任务,提出了基于感知损失的高效网络生成对抗网络(PL-E-GAN)。与其他先进的图像翻译模型不同,PL-E-GAN为图像超分辨率任务提供了通用架构。PL-E-GAN由两个卷积神经网络(cnn)组成,分别是生成网络(Generative network)和判别网络(Discriminator network) Gn和Dn。PL-E-GAN将生成对抗损失和感知对抗损失作为网络的目标函数。这些损失函数的积分经过对抗性训练,网络Gn和Dn交替训练。在许多图像到图像的翻译任务中,研究和测试了PL-E-GAN在几种图像翻译模型上的可行性和优势
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Personal Protective Equipment Detection with Live Camera A Fast and Unbiased Minimalistic Resampling Approach for the Particle Filter Sparse Checkerboard Corner Detection from Global Perspective Comparison of Dental Caries Level Images Classification Performance using KNN and SVM Methods An Insight Into the Rise Time of Exponential Smoothing for Speech Enhancement Methods
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1