检索结果-内蒙古大学图书馆

Factorized Tensor Dictionary Learning for Visual Tensor Data Completion

IEEE TRANSACTIONS ON MULTIMEDIA 2021年 23卷 1225-1238页

作者： Xu, Ruotao Xu, Yong Quan, Yuhui South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Commun & Comp Network Lab Guangdong Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Computat Intelligence & Cy Guangzhou 510006 Peoples R China

This paper aims at developing a dictionary-learning-based method for completing the visual tensor data with missing elements. Traditional dictionary learning approaches suffer from very high computational costs when processing high-dimensional tensor data. Some existing approaches for acceleration impose orthogonality constraints or rank-one decompositions on dictionary atoms;however, the expressibility of the resulting dictionary is rather limited. To address such issues, we propose a convolutional analysis model for tensor dictionary learning, where the update of sparse coefficients during dictionary learning is simple and fast. Furthermore, we propose an orthogonality-constrained convolutional factorization scheme for dictionary construction, in which each tensor dictionary atom is factorized by the convolution of two atoms selected from two orthogonal factor dictionaries respectively. This factorization scheme enables us to efficiently learn an expressive dictionary with over-completeness and non-rank-one atoms. Based on our convolutional analysis model and factorization scheme, an effective yet efficient dictionary learning method is proposed for visual tensor completion. Extensive experiments show that, our method not only outperforms existing dictionary-based approaches with relatively-low time cost, but also outperforms recent low-rank approaches.

关键词： Tensile stress Dictionaries Machine learning Visualization convolutional codes Encoding Analytical models Tensor dictionary learning tensor completion convolutional sparse coding factorized dictionary learning

来源：评论

学校读者我要写书评

暂无评论

A method of reconstructing compressive spectral imaging with a complementary prior constraint

引用

OPTICS COMMUNICATIONS 2024年 550卷

作者： Wang, Pan Li, Jie Qi, Chun Wang, Lin Xi An Jiao Tong Univ Fac Elect & Informat Engn Sch Informat & Commun Engn Xian 710049 Peoples R China

Compressed spectral imaging (CSI) is a technique for acquiring a cube of spectral image data in a single snapshot. In this paper, we propose a reconstruction method for the CSI system that integrates complementary prior constraints on spectral data to significantly enhance the accuracy of reconstructed data. The fundamental con-cepts are as follows: (1) Firstly, by conducting a thorough analysis of the corresponding feature maps of spectral data on the convolution dictionaries, we confirm the feasibility of utilizing the stationary response characteristics of spectral data on the convolution dictionaries as a reconstruction constraint to enhance spectral accuracy. (2) To compensate for the limitations of convolutional sparse coding in reconstructing low-frequency signals, this paper proposes utilizing iterative Total Variation operators to estimate the low-frequency portion of spectral data. This approach results in improved performance in reconstructing low-frequency data and noise suppression. (3) convolutional sparse coding and Total Variation are utilized as constraints for high and low-frequency complementary reconstruction, resulting in a multi-constraint solution problem within the Plug-and-Play framework that simplifies the overall reconstruction process. The proposed method surpasses the state-of-the-art reconstruction methods in both spatial reconstruction quality and spectral accuracy, while also significantly enhancing the level of detail in reconstructed spectral images.

关键词： Compressive spectral imaging convolutional sparse coding Plug -and -Play

来源：评论

学校读者我要写书评

暂无评论

A Novel Interpretable Model via Algorithm Unrolling for Intelligent Fault Diagnosis of Machinery

引用

IEEE SENSORS JOURNAL 2024年第1期24卷 495-505页

作者： Rao, Fengpei Zeng, Ming Cheng, Yiwei China Univ Geosci Sch Mech Engn & Elect Informat Wuhan 430074 Peoples R China China Univ Geosci Shenzhen Res Inst Shenzhen 518057 Peoples R China

Identifying the health state of machinery using sensor information is one of the key tasks for intelligent operation and maintenance of machinery. In recent years, deep learning models have been widely used in this field. However, these models usually lack interpretability. To this end, we use the algorithm unrolling technique to unroll the convolutional version of iterative shrinkage-thresholding algorithm (CISTA) into a neural network called CISTA-Net. The CISTA-Net's structure is determined by the iterative algorithm and thus has a clear theoretical basis. By adding a classification module and a reconstruction module in parallel to its output end, the CISTA-Net is interpretable in terms of both its structure and output. Interpretability analysis through the well-known bearing dataset from the Case Western Reserve University (CWRU) shows that the reconstruction module can enhance the interpretability. In addition, a simple residual block can be optionally added to the input end of the CISTA-Net for feature pre-extraction, resulting in an alternative CISTA-Net called ResCISTA-Net. The ResCISTA-Net is compared with some conventional and interpretable fault diagnosis models on another two mechanical fault diagnosis tasks. Experimental results suggest that: 1) the residual block can not only improve diagnostic accuracy but also prevent performance degradation for some tasks;2) the reconstruction module can also improve diagnostic accuracy;and 3) the ResCISTA-Net performs excellently in terms of diagnostic accuracy, training sample size requirement, and noise robustness.

关键词： Convolution convolutional codes Feature extraction Encoding Kernel Signal processing algorithms Fault diagnosis Algorithm unrolling convolutional sparse coding intelligent fault diagnosis interpretable neural network

来源：评论

学校读者我要写书评

暂无评论

convolutional sparse Coded Dynamic Brain Functional Connectivity

引用

NEURAL PROCESSING LETTERS 2020年第3期52卷 1881-1892页

作者： Yan, Jin Zhu, Yingying Univ Texas Arlington Arlington TX 76019 USA

Functional brain network has been widely studied in many previous work for brain disorder diagnosis and brain network analysis. However, most previous work focus on static dynamic brain network research. Lots of recent work reveals that the brain shows dynamic activity even in resting state. Such dynamic brain functional connectivity reveals discriminative patterns for identifying many brain disorders. Current sliding window based dynamic brain connectivity framework are not easy to be applied to real clinical applications due to many issues: First, how to set up the optimal sliding window size and how to determine the threshold for the brain connectivity patterns. Secondly, how to represent the high dimensional dynamic brain connectivity pattern in a low dimensional representations for diagnosis purpose. Last, how to deal with the different length dynamic brain network patterns especially when the raw data are of different length. In order to address all those above issues, we proposed a new framework, which employs multiple scale sliding windows and automatically learns a sparse and low ran dynamic brain functional connectivity patterns from raw fMRI data. Furthermore, we are able to measure different length dynamic brain functional connectivity patterns in an equal space by learning a sparse coded convolutional filters. We have evaluated our method with state of the art dynamic brain network methods and the results demonstrated the strong potential of our methods for brain disorder diagnosis in real clinical applications.

关键词： Functional magnetic resonance images convolutional sparse coding Dynamic brain network Computer assisted diagnosis

来源：评论

学校读者我要写书评

暂无评论

Online Rain/Snow Removal From Surveillance Videos

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 2029-2044页

作者： Li, Minghan Cao, Xiangyong Zhao, Qian Zhang, Lei Meng, Deyu Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Peoples R China Xi An Jiao Tong Univ Key Lab Intelligent Networks & Network Secur Minist Educ Xian 710049 Peoples R China Macau Univ Sci & Technol Fac Informat Technol Taipa Macau Peoples R China

Video rain/snow removal from surveillance videos is an important task in the computer vision community since rain/snow existed in videos can severely degenerate the performance of many surveillance system. Various methods have been investigated extensively, but most only consider consistent rain/snow under stable background scenes. Rain/snow captured from practical surveillance camera, however, is always highly dynamic in time, and those videos also include occasionally transformed background scenes and background motions caused by waving leaves or water surfaces. To this issue, this paper proposes a novel rain/snow removal approach, which fully considers dynamic statistics of both rain/snow and background scenes taken from a video sequence. Specifically, the rain/snow is encoded as an online multi-scale convolutional sparse coding (OMS-CSC) model, which not only finely delivers the sparse scattering and multi-scale shapes of real rain/snow, but also well distinguish the components of background motion from rain/snow layer. The real-time ameliorated parameters in the model well encodes their temporally dynamic configurations. Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence. The approach so constructed can naturally better adapt to the dynamic rain/snow as well as background changes, and also suitable to deal with the streaming video attributed its online learning mode. The proposed model is formulated in a concise maximum a posterior (MAP) framework and is readily solved by the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art online and offline video rain/snow removal methods, the proposed method achieves best performance on synthetic and real videos datasets both visually and quantitatively. Specifically, our method can

关键词： Videos Rain Task analysis Dynamics Snow convolutional codes Surveillance Multi-scale convolutional sparse coding rain snow removal dynamic background online learning alignment method

来源：评论

学校读者我要写书评

暂无评论

Learning Separable Filters

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2015年第1期37卷 94-106页

作者： Sironi, Amos Tekin, Bugra Rigamonti, Roberto Lepetit, Vincent Fua, Pascal Ecole Polytech Fed Lausanne IC Fac Comp Vis Lab CH-1015 Lausanne Switzerland Graz Univ Technol Inst Comp Graph & Vis A-8010 Graz Austria

Learning filters to produce sparse image representations in terms of overcomplete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of separable ones, thus greatly reducing the computational complexity at no cost in terms of performance. This makes filter learning approaches practical even for large images or 3D volumes, and we show that we significantly outperform state-of-the-art methods on the curvilinear structure extraction task, in terms of both accuracy and speed. Moreover, our approach is general and can be used on generic convolutional filter banks to reduce the complexity of the feature extraction step.

关键词： convolutional sparse coding filter learning features extraction separable convolution segmentation of linear structures image denoising convolutional neural networks tensor decomposition

来源：评论

学校读者我要写书评

暂无评论

Adaptive ADMM for Dictionary Learning in convolutional sparse Representation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2019年第7期28卷 3408-3422页

作者： Peng, Guan-Ju Natl Chung Hsing Univ Dept Appl Math Taichung 402 Taiwan

In this paper, we propose a novel approach to convolutional sparse representation with the aim of resolving the dictionary learning problem. The proposed method, referred to as the adaptive alternating direction method of multipliers (AADMM), employs constraints comprising non-convex, non-smooth terms, such as the l(0)-norm imposed on the coefficients and the unit-norm sphere imposed on the length of each dictionary element. The proposed scheme incorporates a novel parameter adaption scheme that enables ADMM to achieve convergence more quickly, as evidenced by numerical and theoretical analysis. In experiments involving image signal applications, the dictionaries learned using AADMM outperformed those learned using comparable dictionary learning methods.

关键词： convolutional dictionary learning convolutional sparse coding non-convex and non-smooth optimization

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT SEPARABLE FILTER ESTIMATION USING RANK-1 convolutional DICTIONARY LEARNING 28

EFFICIENT SEPARABLE FILTER ESTIMATION USING RANK-1 CONVOLUTI...

引用

IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP)

作者： Silva, Gustavo Quesada, Jorge Rodriguez, Paul Pontificia Univ Catolica Peru Elect Engn Dept Lima Peru

ISBN: (纸本)9781538654774

Natively learned separable filters for convolutional sparse coding (CSC) have recently been shown to provide equivalent reconstruction performance to their non-separable counterparts (as opposed to approximated separable filters), while reducing computational cost. Furthermore, multiple approaches to optimize the Dictionary Update stage of convolutional Dictionary Learning (CDL) methods based on the Accelerated Proximal Gradient (APG) framework have recently been proposed. In this paper, we propose a novel separable filter learning method based on the rank-1 decomposition, and test its performance against the existing separable approaches. In adittion, we evaluate how APG-based variations couple with our proposed method in order to improve computational runtime. Our results show that the filters learned through our proposed method match the performance of other natively-learned separable filters, while providing a significant runtime improvement in the learning process through our APG-based implementation.

关键词： Separable Filter learning convolutional sparse Representation convolutional sparse coding

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Image Super-Resolution via Deep convolutional Transform Learning 32

Multi-modal Image Super-Resolution via Deep Convolutional Tr...

引用

32nd European Signal Processing Conference (EUSIPCO)

作者： Kumar, Kriti Majumdar, Angshul Kumar, A. Anil Chandra, M. Girish TCS Res Pune Maharashtra India IIIT Delhi New Delhi India TCG CREST Inst Adv Intelligence Kolkata India

ISBN: (纸本)9789464593617;9798331519773

Real-world situations often involve processing data from diverse imaging modalities like Multispectral (MS), Near Infrared (NIR), and RGB, each capturing different aspects of the same scene. These modalities often vary in spatial and spectral resolution. Hence, Multi-modal Image Super-Resolution (MISR) techniques are required to improve the spatial/spectral resolution of target modality, taking help from High Resolution (HR) guidance modality that shares common features like textures, edges, and other structures. Traditional MISR approaches using convolutional Neural Networks (CNNs) typically employ an encoder-decoder architecture, which is prone to overfit in data-limited scenarios. This work proposes a novel deep convolutional analysis sparse coding method, utilizing convolutional transforms within a fusion framework that eliminates the need for a decoder network. Thus, reducing the trainable parameters and enhancing the suitability for data-limited application scenarios. A joint optimization framework is proposed, which learns deep convolutional transforms for Low Resolution (LR) images of the target modality and HR images of the guidance modality, along with a fusion transform that combines these transform features to reconstruct HR images of the target modality. In contrast to dictionary-based synthesis sparse coding methods for MISR, the proposed approach offers improved performance with reduced complexity, leveraging the inherent advantages of transform learning. The efficacy of the proposed method is demonstrated using RGB-NIR and RGB-MS datasets, showing superior reconstruction performance compared to state-of-the-art techniques without introducing additional artifacts from the guidance image.

关键词： Multimodal image super-resolution convolutional transform learning Joint optimization convolutional sparse coding Deep models

来源：评论

学校读者我要写书评

暂无评论

LEVERAGING 2D AND 3D CUES FOR FINE-GRAINED OBJECT CLASSIFICATION 23

LEVERAGING 2D AND 3D CUES FOR FINE-GRAINED OBJECT CLASSIFICA...

引用

23rd IEEE International Conference on Image Processing (ICIP)

作者： Wang, Xiaolong Li, Robert (Bo) Currey, Jon Samsung Res Amer Mountain View CA 94043 USA

ISBN: (纸本)9781467399616

Objects in fine-grained categories always share a high degree of shape similarity, making both "localizing discriminative parts" and "learning appearance descriptors" extremely difficult. We propose a framework to leverage 2D+3D cues to handle above two challenges. Towards the goal of image alignment to localize discriminative parts, traditional methods rely on either manual part annotation or image segmentation. Instead, our framework leverages each image's 3D camera pose estimation to align images;Towards the goal of "learning appearance descriptors" confined with small training data and memory/computation cost, we propose an unsupervised convolutional sparse coding (CSC) + manifold learning that significantly reduces model complexity, but still successfully produces highly diverse feature filters like deep neural network. Our experimental results attest the advocated framework's accuracy is comparable to a deep network, demonstrating its great potential on mobile devices.

关键词： Fine-grained object classification 2D+3D cues 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：