检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Alom, Md Zahangir Van Essen, Brian Moody, Adam T. Widemann, David Peter Taha, Tarek M. Univ Dayton Dept Elect & Comp Engn Dayton OH 45469 USA LLNL Livermore CA USA

ISBN: (纸本)9781509061822

Image features can be learned and subsequently used for reconstruction and classification tasks in the fields of machine learning and computer vision. In this work, we propose image reconstruction using convolutional sparse coding (CSC) on IBM's TrueNorth Neuromorphic computing system. CSC explicitly models local interactions through the convolution operations. convolutional kernels define a dictionary and sparse Feature Maps (SFMs) that are generated through a training process. The images are reconstructed with convolutional operations on SFMs and respective kernels. In this paper, we report on experimental results demonstrating promising sparse reconstructions on the IBM Neuromorphic TrueNorth hardware for two different benchmarks: MNIST and CIFAR-10. It is noted that this is the first ever important step towards convolutional sparse coding on neuromorphic hardware.

关键词： convolutional sparse coding sparse features CNN TrueNorth Cognitive System deep network.

来源：评论

学校读者我要写书评

暂无评论

convolutional sparse coding WITH WEIGHTED L1 NORM FOR PHASE RETRIEVAL: ALGORITHM AND ITS DEEP UNFOLDED NETWORK 29

CONVOLUTIONAL SPARSE CODING WITH WEIGHTED L1 NORM FOR PHASE ...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Shi, Baoshun Gao, Yating Jiang, Ke Lian, Qiusheng Yanshan Univ Sch Informat Sci & Engn Qinhuangdao Peoples R China Hebei Key Lab Informat Transmiss & Signal Proc Qinhuangdao Hebei Peoples R China

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Recovering the image of interest from its phaseless measurement is the goal of phase retrieval (PR). Recent PR algorithms that use hand-crafted priors suffer from low-quality reconstructions. To cope with this limitation, we exploit structural priors to propose a novel deep unfolded convolutional sparse coding phase retrieval network. Firstly, we formulate a weighted l(1) norm (WL1) minimization problem utilizing convolutional sparse coding for PR, and solve it by using an iterative algorithm. An inertial epigraph method employing the inertial technique is proposed to solve the PR subproblem. Secondly, differing from updating weights of WL1 by using a fixed inverse proportional function in traditional methods, we learn such a function that can determine these crucial weights via a deep convolutional neural network equipped with the attention mechanism. Finally, we unroll the iterative PR algorithm to build a deep feedforward network architecture. Experiments demonstrate that the resulting model-based deep network can recover higher-quality images, compared with the existing PR algorithms at various noise levels. The testing data and codes are published at https://***/shibaoshun/PRNet.

关键词： Phase retrieval convolutional sparse coding weighted l(1) norm deep unrolled network

来源：评论

学校读者我要写书评

暂无评论

convolutional sparse coding and directional gradient prior based method for single image rain streak removal 8

Convolutional sparse coding and directional gradient prior b...

引用

Conference on Optoelectronic Imaging and Multimedia Technology VIII

作者： Wang, ShengBiao Hua, Nina Li, Jian Zheng, Yuanyuan Xie, Pengfei Wang, Junhao Chen, Huasong Huaiyin Inst Technol Fac Comp & Software Engn Huaian Peoples R China Huaiyin Inst Technol Fac Math & Phys Huaian Peoples R China

ISBN: (数字)9781510646445

ISBN: (纸本)9781510646445;9781510646438

In this paper, we address the rain streak removal from a single image. In order to efficiently detect and remove the annoying rain streaks, we propose a global single-directional gradient prior with the L0 norm to model the rain streak. To preserve the abundant information of the background, we learn a convolutional sparse coding (CSC) to represent the background. Furthermore, we develop an alternating direction method of multipliers (ADMM) to solve multi-variable optimization problems. Experiments on synthesized and real-world images show that the proposed method outperforms state-of-art methods in terms of rain streak removal and background preservation.

关键词： global directional gradient prior convolutional sparse coding dictionary learning ADMM rain streak removal

来源：评论

学校读者我要写书评

暂无评论

Towards understanding residual and dilated dense neural networks via convolutional sparse coding

引用

National Science Review 2021年第3期8卷 127-139页

作者： Zhiyang Zhang Shihua Zhang National Center for Mathematics and Interdisciplinary Sciences Center for Excellence in Mathematical Science Key Laboratory of Random Complex Structures and Data ScienceAcademy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences Center for Excellence in Animal Evolution and Genetics Chinese Academy of Sciences Key Laboratory of Systems Biology Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Chinese Academy of Sciences

convolutional neural network(CNN) and its variants have led to many state-of-the-art results in various ***,a clear theoretical understanding of such networks is still ***,a multilayer convolutional sparse coding(ML-CSC) model has been proposed and proved to equal such simply stacked networks(plain networks).Here,we consider the initialization,the dictionary design and the number of iterations to be factors in each layer that greatly affect the performance of the ML-CSC *** by these considerations,we propose two novel multilayer models:the residual convolutional sparse coding(Res-CSC) model and the mixed-scale dense convolutional sparse coding(MSD-CSC) *** are closely related to the residual neural network(ResNet) and the mixed-scale(dilated) dense neural network(MSDNet),***,we derive the skip connection in the ResNet as a special case of a new forward propagation rule for the ML-CSC *** also find a theoretical interpretation of dilated convolution and dense connection in the MSDNet by analyzing the MSD-CSC model,which gives a clear mathematical understanding of *** implement the iterative soft thresholding algorithm and its fast version to solve the Res-CSC and MSD-CSC *** unfolding operation can be employed for further ***,extensive numerical experiments and comparison with competing methods demonstrate their effectiveness.

关键词： convolutional neural network convolutional sparse coding residual neural network mixed-scale dense neural network dilated convolution dense connection

来源：评论

学校读者我要写书评

暂无评论

Structure-texture image decomposition via non-convex total generalized variation and convolutional sparse coding

引用

VISUAL COMPUTER 2023年第3期39卷 1121-1136页

作者： Wang, Chunxue Xu, Linlin Liu, Ligang Dunhuang Acad Jiuquan Gansu Peoples R China Inner Mongolia Univ Finance & Econ Sch Comp Informat Management Hohhot Inner Mongolia Peoples R China Univ Sci & Technol China Sch Math Sci Hefei Anhui Peoples R China

Image decomposition is a fundamental but challenging ill-posed problem in image processing and has been widely applied to compression, enhancement, texture removal, etc. In this paper, we introduce a novel structure-texture image decomposition model via non-convex total generalized variation regularization (NTGV) and convolutional sparse coding (CSC). NTGV aims to characterize the detailed-preserved structural component ameliorating the staircasing artifacts existing in total variation-based models, and CSC aims to characterize image fine-scale textures. Moreover, we incorporate both structure-aware and texture-aware measures to well distinguish structural and textural component. The proposed model is numerically implemented by an alternating minimization scheme based on alternating direction method of multipliers. Experimental results demonstrate the effectiveness of our approach on several applications including texture removal, high dynamic range image tone mapping, detail enhancement and non-photorealistic abstraction.

关键词： Structure-texture image decomposition Non-convex total generalized variation regularization convolutional sparse coding Alternating minimization scheme Detail-preserving

来源：评论

学校读者我要写书评

暂无评论

3D Localization for Light-Field Microscopy via convolutional sparse coding on Epipolar Images

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2020年 6卷 1017-1032页

作者： Song, Pingfan Jadan, Herman Verinaz Howe, Carmel L. Quicke, Peter Foust, Amanda J. Dragotti, Pier Luigi Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England Imperial Coll London Dept Bioengn London SW7 2AZ England Imperial Coll London Ctr Neurotechnol London SW7 2AZ England

Light-field microscopy (LFM) is a type of all-optical imaging system that is able to capture 4D geometric information of light rays and can reconstruct a 3D model from a single snapshot. In this paper, we propose a new 3D localization approach to effectively detect 3D positions of neuronal cells from a single light-field image with high accuracy and outstanding robustness to light scattering. This is achieved by constructing a depth-aware dictionary and by combining it with convolutional sparse coding. Specifically, our approach includes 3 key parts: light-field calibration, depth-aware dictionary construction, and localization based on convolutional sparse coding (CSC). In the first part, an observed raw light-field image is calibrated and then decoded into a two-plane parameterized 4D format which leads to the epi-polar plane image (EPI). The second part involves simulating a set of light-fields using a wave-optics forward model for a ball-shaped volume that is located at different depths. Then, a depth-aware dictionary is constructed where each element is a synthetic EPI associated to a specific depth. Finally, by taking full advantage of the sparsity prior and shift-invariance property of EPI, 3D localization is achieved via convolutional sparse coding on an observed EPI with respect to the depth-aware EPI dictionary. We evaluate our approach on both non-scattering specimen (fluorescent beads suspended in agarose gel) and scattering media (brain tissues of genetically encoded mice). Extensive experiments demonstrate that our approach can reliably detect the 3D positions of granular targets with small Root Mean Square Error (RMSE), high robustness to optical aberration and light scattering in mammalian brain tissues.

关键词： Light-field microscopy epi-polar plane image convolutional sparse coding depth-aware dictionary

来源：评论

学校读者我要写书评

暂无评论

convolutional Neural Networks Analyzed via convolutional sparse coding

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2017年第1期18卷 1-52页

作者： Papyan, Vardan Romano, Yaniv Elad, Michael Technion Israel Inst Technol Dept Comp Sci IL-32000 Haifa Israel Technion Israel Inst Technol Dept Elect Engn IL-32000 Haifa Israel

convolutional neural networks (CNN) have led to many state-of-the-art results spanning through various fields. However, a clear and profound theoretical understanding of the forward pass, the core algorithm of CNN, is still lacking. In parallel, within the wide field of sparse approximation, convolutional sparse coding (CSC) has gained increasing attention in recent years. A theoretical study of this model was recently conducted, establishing it as a reliable and stable alternative to the commonly practiced patch-based processing. Herein, we propose a novel multi-layer model, ML-CSC, in which signals are assumed to emerge from a cascade of CSC layers. This is shown to be tightly connected to CNN, so much so that the forward pass of the CNN is in fact the thresholding pursuit serving the ML-CSC model. This connection brings a fresh view to CNN, as we are able to attribute to this architecture theoretical claims such as uniqueness of the representations throughout the network, and their stable estimation, all guaranteed under simple local sparsity conditions. Lastly, identifying the weaknesses in the above pursuit scheme, we propose an alternative to the forward pass, which is connected to deconvolutional and recurrent networks, and also has better theoretical guarantees.

关键词： Deep Learning convolutional Neural Networks Forward Pass sparse Representation convolutional sparse coding Thresholding Algorithm Basis Pursuit

来源：评论

学校读者我要写书评

暂无评论

Two Layer Tensor Form convolutional sparse coding for Stereo Matching

引用

IEEE ACCESS 2021年 9卷 109396-109406页

作者： Cheng, Chunbo Cui, Wenjing Huazhong Univ Sci & Technol Sch Math & Stat Wuhan 430074 Peoples R China Hubei Polytech Univ Sch Math & Phys Huangshi 435000 Hubei Peoples R China

Stereo matching is an important research topic in the field of computer vision. It recovers depth information from a pair of color images. Unfortunately, converting multi-dimensional (more than two-dimensional) data into two-dimensional data, such formulations ignore the spatial structure of multi-dimensional images/data. Tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features that helps to improve the performance of the algorithm. Therefore, it is very important to establish a deep tensor model. In this paper, we propose a two layer tensor form convolutional sparse coding model, which can automatically learn the deep convolutional kernel. Based on the learned two layer convolutional kernels, a two-layer dictionary learning model is established. Then, a new weighted matching cost method is constructed, which combines shallow and deep features. The experimental results on the Middlebury benchmark v2 and Middlebury benchmark v3 show that the proposed two layer tensor convolutional sparse coding is effective for stereo matching.

关键词： Tensors convolutional codes Encoding Feature extraction Kernel Convolution Correlation Stereo matching high-order tensor convolutional sparse coding deep learning dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Deep residual constrained reconstruction via learned convolutional sparse coding for low-dose CT imaging

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2023年第1期85卷

作者： Liu, Jin Zhang, Tingyu Kang, Yanqin Wang, Yong Zhang, Yikun Hu, Dianlin Chen, Yang Anhui Polytech Univ Coll Comp & Informat Wuhu Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China Southeast Univ Sch Cyber Sci & Engn Nanjing Peoples R China

Low-dose computed tomography (LDCT) holds great potential to reduce radiation dose damage. However, LDCT degrades the signal-to-noise ratio (SNR) of projection and compromises the reconstruction image quality. This paper proposes a deep residual-constrained reconstruction (DRCR) framework via learned convolutional sparse coding (LCSC) for LDCT imaging. DRCR consists of multiple iteration blocks, and each iteration contains three modules: image update, residual correction and convolution representation modules. First, the image update module updates the reconstruction image with a DL-based prior constraint. Then, the residual correction module attempts to accurately estimate the residual features after mapping the projection errors into the image domain. Finally, the LCSC network is applied for feature map and filter updating to further constrain the image update process. To further improve the performance of DRCR, the perceptual losses of the image domain and projection domain are considered in the optimized model. The results obtained on two datasets show the competitive performance of the proposed framework, with a 0.5 dB PSNR margin, 0.007 SSIM margin, and 1.7 FID margin on the MAYO dataset and a 0.5 dB PSNR margin, 0.011 SSIM margin and 2.4 FID margin on the UIH dataset.

关键词： Low -dose CT Image reconstruction Residual constrained convolutional sparse coding

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Energy Disaggregation Via convolutional sparse coding

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 4303-4310页

作者： Aarset, Christian Habring, Andreas Holler, Martin Mitter, Mario Karl Franzens Univ Graz Inst Math & Sci Comp A-8010 Graz Austria Solgenium OG A-4040 Linz Austria

In this work, a method for unsupervised energy disaggregation in private households equipped with smart meters is proposed. The method aims to classify power consumption as active or passive, granting the ability to report on the residents' activity and presence without direct interaction. This lays the foundation for applications like non-intrusive health monitoring of private homes. The proposed method is based on minimizing a suitable energy functional, for which the iPALM (inertial proximal alternating linearized minimization) algorithm is employed, demonstrating that various conditions guaranteeing convergence are satisfied. In order to confirm feasibility of the proposed method, experiments on semi-synthetic test data sets and a comparison to existing methods are provided.

关键词： Hidden Markov models Power demand Smart meters Minimization Energy consumption Encoding Convolution Energy disaggregation non-intrusive load monitoring health monitoring convolutional sparse coding

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：