In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training cos...In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training costs and long inference times, limiting their practical application in denoising tasks. This paper proposes a new dual convolutional denoising network with skip connections(DECDNet), which achieves an ideal balance between denoising effect and network complexity. The proposed DECDNet consists of a noise estimation network, a multi-scale feature extraction network, a dual convolutional neural network, and dual attention mechanisms. The noise estimation network is used to estimate the noise level map, and the multi-scale feature extraction network is combined to improve the model's flexibility in obtaining image features. The dual convolutional neural network branch design includes convolution and dilated convolution interactive connections, with the lower branch consisting of dilated convolution layers, and both branches using skip connections. Experiments show that compared with other models, the proposed DECDNet achieves superior PSNR and SSIM values at all compared noise levels, especially at higher noise levels, showing robustness to images with higher noise levels. It also demonstrates better visual effects, maintaining a balance between denoising and detail preservation.展开更多
Convolutional neural networks(CNNs)have shown tremendous progress and performance in recent years.Since emergence,CNNs have exhibited excellent performance in most of classification and segmentation tasks.Currently,th...Convolutional neural networks(CNNs)have shown tremendous progress and performance in recent years.Since emergence,CNNs have exhibited excellent performance in most of classification and segmentation tasks.Currently,the CNN family includes various architectures that dominate major vision-based recognition tasks.However,building a neural network(NN)by simply stacking convolution blocks inevitably limits its optimization ability and introduces overfitting and vanishing gradient problems.One of the key reasons for the aforementioned issues is network singularities,which have lately caused degenerating manifolds in the loss landscape.This situation leads to a slow learning process and lower performance.In this scenario,the skip connections turned out to be an essential unit of the CNN design to mitigate network singularities.The proposed idea of this research is to introduce skip connections in NN architecture to augment the information flow,mitigate singularities and improve performance.This research experimented with different levels of skip connections and proposed the placement strategy of these links for any CNN.To prove the proposed hypothesis,we designed an experimental CNN architecture,named as Shallow Wide ResNet or SRNet,as it uses wide residual network as a base network design.We have performed numerous experiments to assess the validity of the proposed idea.CIFAR-10 and CIFAR-100,two well-known datasets are used for training and testing CNNs.The final empirical results have shown a great many of promising outcomes in terms of performance,efficiency and reduction in network singularities issues.展开更多
In multicellular and even single-celled organisms,individual components are interconnected at multiscale levels to produce enormously complex biological networks that help these systems maintain homeostasis for develo...In multicellular and even single-celled organisms,individual components are interconnected at multiscale levels to produce enormously complex biological networks that help these systems maintain homeostasis for development and environmental adaptation.Systems biology studies initially adopted network analysis to explore how relationships between individual components give rise to complex biological processes.Network analysis has been applied to dissect the complex connectivity of mammalian brains across different scales in time and space in The Human Brain Project.In plant science,network analysis has similarly been applied to study the connectivity of plant components at the molecular,subcellular,cellular,organic,and organism levels.Analysis of these multiscale networks contributes to our understanding of how genotype determines phenotype.In this review,we summarized the theoretical framework of plant multiscale networks and introduced studies investigating plant networks by various experimental and computational modalities.We next discussed the currently available analytic methodologies and multi-level imaging techniques used to map multiscale networks in plants.Finally,we highlighted some of the technical challenges and key questions remaining to be addressed in this emerging field.展开更多
针对医学影像超分辨率重建过程中细节丢失导致的模糊问题,提出了一种基于深度残差生成对抗网络(GAN)的医学影像超分辨率算法。首先,算法包括生成器网络和判别器网络,生成器网络生成高分辨率图像,判别器网络辨别图像真伪。然后,通过设计...针对医学影像超分辨率重建过程中细节丢失导致的模糊问题,提出了一种基于深度残差生成对抗网络(GAN)的医学影像超分辨率算法。首先,算法包括生成器网络和判别器网络,生成器网络生成高分辨率图像,判别器网络辨别图像真伪。然后,通过设计生成器网络的上采样采用缩放卷积来削弱棋盘效应,并去掉标准残差块中的批量规范化层以优化网络;进一步增加判别器网络中特征图数量以加深网络等方面提高网络性能。最后,用生成损失和判别损失来不断优化网络,指导生成高质量的图像。实验结果表明,对比双线性内插、最近邻插值、双三次插值法、基于深度递归神经网络、基于生成对抗网络的超分辨率方法(SRGAN),所提算法重建出了纹理更丰富、视觉更逼真的图像。相比SRGAN方法,所提算法在峰值信噪比(PSNR)和结构相似度(SSIM)上有0.21 d B和0.32%的提升。所提算法为医学影像超分辨率的理论研究提供了深度残差生成对抗网络的方法,在其实际应用中可靠、有效。展开更多
基金funded by National Nature Science Foundation of China,grant number 61302188。
文摘In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training costs and long inference times, limiting their practical application in denoising tasks. This paper proposes a new dual convolutional denoising network with skip connections(DECDNet), which achieves an ideal balance between denoising effect and network complexity. The proposed DECDNet consists of a noise estimation network, a multi-scale feature extraction network, a dual convolutional neural network, and dual attention mechanisms. The noise estimation network is used to estimate the noise level map, and the multi-scale feature extraction network is combined to improve the model's flexibility in obtaining image features. The dual convolutional neural network branch design includes convolution and dilated convolution interactive connections, with the lower branch consisting of dilated convolution layers, and both branches using skip connections. Experiments show that compared with other models, the proposed DECDNet achieves superior PSNR and SSIM values at all compared noise levels, especially at higher noise levels, showing robustness to images with higher noise levels. It also demonstrates better visual effects, maintaining a balance between denoising and detail preservation.
文摘Convolutional neural networks(CNNs)have shown tremendous progress and performance in recent years.Since emergence,CNNs have exhibited excellent performance in most of classification and segmentation tasks.Currently,the CNN family includes various architectures that dominate major vision-based recognition tasks.However,building a neural network(NN)by simply stacking convolution blocks inevitably limits its optimization ability and introduces overfitting and vanishing gradient problems.One of the key reasons for the aforementioned issues is network singularities,which have lately caused degenerating manifolds in the loss landscape.This situation leads to a slow learning process and lower performance.In this scenario,the skip connections turned out to be an essential unit of the CNN design to mitigate network singularities.The proposed idea of this research is to introduce skip connections in NN architecture to augment the information flow,mitigate singularities and improve performance.This research experimented with different levels of skip connections and proposed the placement strategy of these links for any CNN.To prove the proposed hypothesis,we designed an experimental CNN architecture,named as Shallow Wide ResNet or SRNet,as it uses wide residual network as a base network design.We have performed numerous experiments to assess the validity of the proposed idea.CIFAR-10 and CIFAR-100,two well-known datasets are used for training and testing CNNs.The final empirical results have shown a great many of promising outcomes in terms of performance,efficiency and reduction in network singularities issues.
基金supported by the National Natural Science Foundation of China(31530084,32000558,32000483,and31800504)the Programme of Introducing Talents of Discipline to Universities(111 project,B13007)the China Postdoctoral Science Foundation Grant(2019M660494)。
文摘In multicellular and even single-celled organisms,individual components are interconnected at multiscale levels to produce enormously complex biological networks that help these systems maintain homeostasis for development and environmental adaptation.Systems biology studies initially adopted network analysis to explore how relationships between individual components give rise to complex biological processes.Network analysis has been applied to dissect the complex connectivity of mammalian brains across different scales in time and space in The Human Brain Project.In plant science,network analysis has similarly been applied to study the connectivity of plant components at the molecular,subcellular,cellular,organic,and organism levels.Analysis of these multiscale networks contributes to our understanding of how genotype determines phenotype.In this review,we summarized the theoretical framework of plant multiscale networks and introduced studies investigating plant networks by various experimental and computational modalities.We next discussed the currently available analytic methodologies and multi-level imaging techniques used to map multiscale networks in plants.Finally,we highlighted some of the technical challenges and key questions remaining to be addressed in this emerging field.
文摘针对医学影像超分辨率重建过程中细节丢失导致的模糊问题,提出了一种基于深度残差生成对抗网络(GAN)的医学影像超分辨率算法。首先,算法包括生成器网络和判别器网络,生成器网络生成高分辨率图像,判别器网络辨别图像真伪。然后,通过设计生成器网络的上采样采用缩放卷积来削弱棋盘效应,并去掉标准残差块中的批量规范化层以优化网络;进一步增加判别器网络中特征图数量以加深网络等方面提高网络性能。最后,用生成损失和判别损失来不断优化网络,指导生成高质量的图像。实验结果表明,对比双线性内插、最近邻插值、双三次插值法、基于深度递归神经网络、基于生成对抗网络的超分辨率方法(SRGAN),所提算法重建出了纹理更丰富、视觉更逼真的图像。相比SRGAN方法,所提算法在峰值信噪比(PSNR)和结构相似度(SSIM)上有0.21 d B和0.32%的提升。所提算法为医学影像超分辨率的理论研究提供了深度残差生成对抗网络的方法,在其实际应用中可靠、有效。
