检索结果-内蒙古大学图书馆

A Greedy Approach to l0,∞-Based convolutional sparse coding

SIAM JOURNAL ON IMAGING SCIENCES 2019年第1期12卷 186-210页

作者： Plaut, Elad Giryes, Raja Tel Aviv Univ Sch Elect Engn IL-6997801 Tel Aviv Israel

sparse coding techniques for image processing traditionally rely on the processing of small overlapping patches separately, followed by averaging. This has the disadvantage that the reconstructed image no longer obeys the sparsity prior used in the processing. For this purpose convolutional sparse coding has been introduced, where a shift-invariant dictionary is used and the sparsity of the recovered image is maintained. Most such strategies target the l(0) "norm" or the l(1) norm of the whole image, which may create an imbalanced sparsity across various regions in the image. In order to face this challenge, the l(0,infinity) "norm" has been proposed as an alternative that "operates locally while thinking globally." The approaches taken for tackling the nonconvexity of these optimization problems have been using either a convex relaxation or local pursuit algorithms. In this paper, we present an efficient greedy method for sparse coding and dictionary learning, which is specifically tailored to l(0,infinity) and is based on matching pursuit. We demonstrate the usage of our approach in salt-and-pepper noise removal and image inpainting.

关键词： convolutional sparse coding global modeling local processing greedy algorithms sparse representations

来源：评论

学校读者我要写书评

暂无评论

Single image super-resolution based on adaptive convolutional sparse coding and convolutional neural networks

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2019年 58卷 651-661页

作者： Zhao, Jianwei Chen, Chen Zhou, Zhenghua Cao, Feilong China Jiliang Univ Dept Informat Sci & Math Hangzhou 310018 Zhejiang Peoples R China

The convolutional sparse coding-based super-resolution (CSC-SR) method has shown its good performance in single image super-resolution. It divides the low-resolution (LR) image into low-frequency part and the high-frequency part, and reconstructs their corresponding high-resolution (HR) image with bicubic interpolation and convolutional sparse coding (CSC) method, respectively. This paper is devoted to improve the performance of CSC-SR method. As convolutional neural network (CNN) can reveal the mapping relation between the LR image and the HR image for the low-frequency part better, we replace the bicubic interpolation with CNN to reconstruct the HR image for the low-frequency part. In addition, we propose an adaptive CSC method to reconstruct the HR image for the high-frequency part. We name our proposed super-resolution method as hybrid adaptive convolutional sparse coding-based super-resolution (HACSC-SR) method. Many comparison experiments illustrate that our proposed HACSC-SR method is superior to CSC-SR, CNN as well as several existing super-resolution methods. (C) 2018 Elsevier Inc. All rights reserved.

关键词： Super-resolution convolutional sparse coding convolutional neural network Adaptive

来源：评论

学校读者我要写书评

暂无评论

Revisiting convolutional sparse coding for Image Denoising: From a Multi-Scale Perspective

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 1202-1206页

作者： Xu, Jingyi Deng, Xin Xu, Mai Beihang Univ Sch Cyber Sci & Technol Beijing 100190 Peoples R China Beihang Univ Dept Elect Informat Engn Beijing 100190 Peoples R China

Recently, convolutional sparse coding (CSC) has shown great success in many image processing tasks, such as image super-resolution and image separation. However, it performs poorly in image denoising task. In this letter, we provide a new insight for CSC denoising by revisiting the CSC from a multi-scale perspective. We propose a multi-scale CSC model for image denoising. By unrolling the multi-scale solution into a learnable network, we obtain an interpretable lightweight multi-scale network, namely MCSCNet. Experimental results show that the proposed MCSCNet significantly advances the denoising performance, with an average PSNR improvement of 0.32 dB over the state-of-the-art (SOTA) CSC based method. In addition, our MCSCNet is on par with many SOTA deep learning based methods, with less network parameters and lower FLOPs. The ablation study also validates the effectiveness of the multi-scale CSC mechanism.

关键词： Image denoising Dictionaries convolutional codes Task analysis Convolution Image reconstruction Mathematical models convolutional sparse coding image denoising

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Transfer Learning via Multi-Scale convolutional sparse coding for Biomedical Applications

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2018年第5期40卷 1182-1194页

作者： Chang, Hang Han, Ju Zhong, Cheng Snijders, Antoine M. Mao, Jian-Hua Lawrence Berkeley Natl Lab Berkeley Biomed Data Sci Ctr Biol Syst & Engn Div Berkeley CA 94720 USA

The capabilities of (I) learning transferable knowledge across domains;and (II) fine-tuning the pre-learned base knowledge towards tasks with considerably smaller data scale are extremely important. Many of the existing transfer learning techniques are supervised approaches, among which deep learning has the demonstrated power of learning domain transferrable knowledge with large scale network trained on massive amounts of labeled data. However, in many biomedical tasks, both the data and the corresponding label can be very limited, where the unsupervised transfer learning capability is urgently needed. In this paper, we proposed a novel multi-scale convolutional sparse coding (MSCSC) method, that (I) automatically learns filter banks at different scales in a joint fashion with enforced scale-specificity of learned patterns;and (II) provides an unsupervised solution for learning transferable base knowledge and fine-tuning it towards target tasks. Extensive experimental evaluation of MSCSC demonstrates the effectiveness of the proposed MSCSC in both regular and transfer learning tasks in various biomedical domains.

关键词： Transfer learning sharable information convolutional sparse coding deep learning biomedical application brain tumors low dose ionizing radiation (LDIR) mouse model breast cancer subtypes

来源：评论

学校读者我要写书评

暂无评论

Image classification via convolutional sparse coding

引用

VISUAL COMPUTER 2023年第5期39卷 1731-1744页

作者： Nozaripour, Ali Soltanizadeh, Hadi Semnan Univ Dept Elect Comp Engn Semnan *** Iran Semnan Univ Fac Elect Comp Engn Semnan *** Iran

The convolutional sparse coding (CSC) model has recently attracted a lot of attention in the signal and image processing communities. Since, in traditional sparse coding methods, a significant assumption is that all input samples are independent, so it is not well for most dependent works. In such cases, CSC models are a good choice. In this paper, we proposed a novel CSC-based classification model which combines the local block coordinate descent (LoBCoD) algorithm with the classification strategy. For this, in the training phase, the convolutional dictionary atoms (filters) of each class are learned by all training samples of the same class. In the test phase, the label of the query sample can be determined based on the reconstruction error of the filters related to every subject. Experimental results on five benchmark databases at the different number of training samples clearly demonstrate the superiority of our method to many state-of-the-art classification methods. Besides, we have shown that our method is less dependent on the number of training samples and therefore it can better work than other methods in small databases with fewer samples. For instance, increases of 26.27%, 18.32%, 11.35%, 13.5%, and 19.3% in recognition rates are observed for our method when compared to conventional SRC for five used databases at the least number of training samples per class.

关键词： convolutional sparse coding sparse representation Image classification Filters Feature map

来源：评论

学校读者我要写书评

暂无评论

Ultrasonic defect characterization using time-domain scattering matrices and convolutional sparse coding

引用

NDT & E INTERNATIONAL 2022年 131卷

作者： Bai, Long Liu, Nanxin Guo, Changrong Xu, Jianfeng Huazhong Univ Sci & Technol Sch Mech Sci & Engn State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China

In this paper, the use of the time-domain scattering matrix for ultrasonic characterization of defects is explored. An approach based on convolutional sparse coding is proposed for extraction of the shift-invariant features of the time-domain scattering matrix. The results of a simulation show that the proposed approach can be reliably used for classification of the rough cracks. In addition, the mean sizing error and its standard deviation are also reduced compared with the use of the frequency domain scattering matrix. In experiments, a 1.5 mm slot and 1.5 mm elliptical defect were sized to within 0.25 mm using a 2.5 MHz, 64 element linear array with an element pitch of 0.5 mm. Excellent sizing results were obtained for inclined slots with a large orientation angle (i.e. 60 degrees).

关键词： Defect characterization Scattering matrix convolutional sparse coding Rough cracks Volumetric defects

来源：评论

学校读者我要写书评

暂无评论

Scalable Online convolutional sparse coding

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2018年第10期27卷 4850-4859页

作者： Wang, Yaqing Yao, Quanming Kwok, James T. Ni, Lionel M. Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China 4Paradigm Inc Beijing Peoples R China Univ Macau Dept Comp & Informat Sci Macau Peoples R China

convolutional sparse coding (CSC) improves sparse coding by learning a shift-invariant dictionary from the data. However, most existing CSC algorithms operate in the batch mode and are computationally expensive. In this paper, we alleviate this problem by online learning. The key is a reformulation of the CSC objective so that convolution can be handled easily in the frequency domain, and much smaller history matrices are needed. To solve the resultant optimization problem, we use the alternating direction method of multipliers (ADMMs), and its subproblems have efficient closed-form solutions. Theoretical analysis shows that the learned dictionary converges to a stationary point of the optimization problem. Extensive experiments are performed on both the standard CSC benchmark data sets and much larger data sets such as the ImageNet. Results show that the proposed algorithm outperforms the state-of-the-art batch and online CSC methods. It is more scalable, has faster convergence, and better reconstruction performance.

关键词： Online learning convolutional sparse coding dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Variations on the convolutional sparse coding Model

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2020年 68卷 519-528页

作者： Rey-Otero, Ives Sulam, Jeremias Elad, Michael Technion Israel Inst Technol Dept Comp Sci IL-32000 Haifa Israel

Over the past decade, the celebrated sparse representation model has achieved impressive results in various signal and image processing tasks. A convolutional version of this model, termed convolutional sparse coding (CSC), has been recently reintroduced and extensively studied. CSC brings a natural remedy to the limitation of typical sparse enforcing approaches of handling global and high-dimensional signals by local, patch-based, processing. While the classic field of sparse representations has been able to cater for the diverse challenges of different signal processing tasks by considering a wide range of problem formulations, almost all available algorithms that deploy the CSC model consider the same problem form. As we argue in this paper, this CSC pursuit formulation is also too restrictive as it fails to explicitly exploit some local characteristics of the signal. This work expands the range of formulations for the CSC model by proposing two convex alternatives that merge global norms with local penalties and constraints. The main contribution of this work is the derivation of efficient and provably converging algorithms to solve these new sparse coding formulations.

关键词： sparse representation convolutional sparse coding parallel proximal algorithm convex optimization

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of l0,∞-Norm Based convolutional sparse coding Using Stripe Coherence

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2020年 68卷 5810-5823页

作者： Fu, Yuli Zhu, Tao Xiang, Youjun Chen, Zhen Cai, Lei South China Univ Technol Sch Elect & Informat Engn Guangzhou 510640 Peoples R China

Theoretical guarantees for the l(0,infinity)-pseudo-norm based convolutional sparse coding have been established in a recent work. However, the stability analysis in the noisy case via the stripe coherence is absent. This coherence is a stronger characterization of the convolutional dictionary, and a considerably more informative measure than the standard global mutual coherence. The present paper supplements this missing part. Formally, three main results together with their proofs are given. The first one is for the stability of the solution to the P-0,infinity(epsilon) problem, the second one and the third one are for the stable recovery of orthogonal matching pursuit (OMP) algorithm in the presence of noise. Under a reasonable assumption, the first two results are compared with the corresponding two that use the global mutual coherence in the previous work, respectively, showing the advantages of our results: 1) the stability guarantee conditions are at least as strong as the existing ones;2) the upper-bound of the distance between the true sparse vector and the solution to the P-0,infinity(epsilon) problem is tighter than the counterpart, so is the one between the true sparse vector and the solution obtained byOMP. Moreover, the second result is compared with the third one, stressing the difference in the restriction on noise energy. Also, some experiments are presented to intuitively compare the aforesaid upper-bounds.

关键词： Stability analysis l(0,infinity)-norm convolutional sparse coding stripe coherence

来源：评论

学校读者我要写书评

暂无评论

Generalized convolutional sparse coding With Unknown Noise

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2020年 29卷 5386-5395页

作者： Wang, Yaqing Kwok, James T. Ni, Lionel M. Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Baidu Res Business Intelligence Lab Beijing 100085 Peoples R China Natl Engn Lab Deep Learning Technol & Applicat Beijing 100085 Peoples R China

convolutional sparse coding (CSC) can learn representative shift-invariant patterns from data. However, existing CSC methods assume the Gaussian noise, which can be restrictive in some challenging applications. In this paper, we propose a generalized CSC model capable of handling complicated unknown noise. The noise is modeled by the Gaussian mixture model, which can approximate any continuous probability density function. The Expectation-Maximization algorithm is used to solve the resultant learning problem. For efficient optimization, the crux is to speed up the convolution in the frequency domain while keeping the other computations involving the weight matrix in the spatial domain. We design an efficient solver for the weighted CSC problem in the M-step. The dictionary and codes are updated simultaneously by an efficient nonconvex accelerated proximal gradient algorithm. The resultant procedure, called generalized convolutional sparse coding (GCSC), obtains the same space complexity and a smaller running time than existing CSC methods (which are limited to the Gaussian noise). Extensive experiments on synthetic and real-world noisy data sets validate that GCSC can model the noise effectively and obtain high-quality filters and representations.

关键词： convolutional sparse coding noise modeling Gaussian mixture model

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：