Drop-DIP: A single-image denoising method based on deep image prior

IF 2.5 2区 数学 Q1 MATHEMATICS
Xueding Zhang, Zhemin Li, Hongxia Wang
{"title":"Drop-DIP: A single-image denoising method based on deep image prior","authors":"Xueding Zhang, Zhemin Li, Hongxia Wang","doi":"10.23952/jnva.7.2023.4.04","DOIUrl":null,"url":null,"abstract":". Over the past few years, deep learning methods have emerged as powerful image denoising tools. Among them, unsupervised deep learning without external training data is more practical and challenging. Reducing noisy overfitting is challenging due to single-image unsupervised learning is prone to overfitting. In this paper, we propose a method named drop-DIP combing Deep Image Prior (DIP) with drop-out for the first time to solve the above problems. In our method, we construct new network training pairs by performing drop-out training on the Bernoulli sampling of the input and output, and then construct a regularization term by using the corrected bias of the output and the generated prior. Finally, update the parameters through the Alternating Direction Method of Multipliers (ADMM) algorithm. Experiments demonstrate that drop-DIP can alleviate the overfitting difficulty in DIP, facilitate the early stopping of the network, and is applicable to different noise models. Furthermore, our method has good performance on Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS) metrics validated by two different datasets.","PeriodicalId":48488,"journal":{"name":"Journal of Nonlinear and Variational Analysis","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nonlinear and Variational Analysis","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.23952/jnva.7.2023.4.04","RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICS","Score":null,"Total":0}
引用次数: 0

Abstract

. Over the past few years, deep learning methods have emerged as powerful image denoising tools. Among them, unsupervised deep learning without external training data is more practical and challenging. Reducing noisy overfitting is challenging due to single-image unsupervised learning is prone to overfitting. In this paper, we propose a method named drop-DIP combing Deep Image Prior (DIP) with drop-out for the first time to solve the above problems. In our method, we construct new network training pairs by performing drop-out training on the Bernoulli sampling of the input and output, and then construct a regularization term by using the corrected bias of the output and the generated prior. Finally, update the parameters through the Alternating Direction Method of Multipliers (ADMM) algorithm. Experiments demonstrate that drop-DIP can alleviate the overfitting difficulty in DIP, facilitate the early stopping of the network, and is applicable to different noise models. Furthermore, our method has good performance on Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS) metrics validated by two different datasets.
Drop-DIP:一种基于深度图像先验的单图像去噪方法
. 在过去的几年里,深度学习方法已经成为强大的图像去噪工具。其中,无外部训练数据的无监督深度学习更具实用性和挑战性。由于单图像无监督学习容易产生过拟合,减少噪声过拟合是一项挑战。本文首次提出了一种将Deep Image Prior (DIP)与drop-out相结合的drop-DIP方法来解决上述问题。在我们的方法中,我们通过对输入和输出的伯努利采样进行drop-out训练来构建新的网络训练对,然后利用输出的修正偏差和生成的先验构造正则化项。最后,通过交替方向乘法器(ADMM)算法更新参数。实验表明,drop-DIP可以缓解DIP的过拟合困难,有利于网络的早期停止,并且适用于不同的噪声模型。此外,我们的方法在峰值信噪比(PSNR)、结构相似度(SSIM)和学习感知图像补丁相似度(LPIPS)指标上具有良好的性能,并通过两个不同的数据集验证。
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
CiteScore
3.30
自引率
3.40%
发文量
10
×
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