检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2017年第1期18卷

作者： Vardan Papyan Yaniv Romano Michael Elad Department of Computer Science Technion - Israel Institute of Technology Technion City 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： basis pursuit convolutional neural networks convolutional sparse coding deep learning forward pass sparse representation thresholding algorithm

来源：评论

学校读者我要写书评

暂无评论

PIANO MUSIC TRANSCRIPTION WITH FAST convolutional sparse coding 25

PIANO MUSIC TRANSCRIPTION WITH FAST CONVOLUTIONAL SPARSE COD...

引用

IEEE International Workshop on Machine Learning for Signal Processing

作者： Cogliati, Andrea Duan, Zhiyao Wohlberg, Brendt Univ Rochester Rochester NY USA Los Alamos Natl Lab Los Alamos NM USA

ISBN: (纸本)9781467374545

Automatic music transcription (AMT) is the process of converting an acoustic musical signal into a symbolic musical representation, such as a MIDI file, which contains the pitches, the onsets and offsets of the notes and, possibly, their dynamics and sources (i.e., instruments). Most existing algorithms for AMT operate in the frequency domain, which introduces the well known time/frequency resolution trade-off of the Short Time Fourier Transform and its variants. In this paper, we propose a time-domain transcription algorithm based on an efficient convolutional sparse coding algorithm in an instrumentspecific scenario, i.e., the dictionary is trained and tested on the same piano. The proposed method outperforms a current state-of-the-art AMT method by over 26% in F-measure, achieving a median Fmeasure of 93.6%, and drastically increases both time and frequency resolutions, especially for the lowest octaves of the piano keyboard.

关键词： Automatic Music Transcription convolutional sparse coding Shift Invariant sparse Representation

来源：评论

学校读者我要写书评

暂无评论

Video Anomaly Detection using Selective Spatio-Temporal Interest Points and convolutional sparse coding

Video Anomaly Detection using Selective Spatio-Temporal Inte...

引用

IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Cahyadi, Rudy Fadlil, Junaidillah Natl Taiwan Univ Sci & Technol Dept Comp Sci & Informat Engn Taipei Taiwan

ISBN: (纸本)9781467396189

Finding substantial features is a significant approach to cope the challenges of video anomaly detection and localization. The specific important representation are selected to detect an event in video. State-of-the-art models explore this fashion by do seeking interest points both spatially and temporally. However, it has to very selective towards undesired object or background. Selective Spatio-Temporal Interest Points (SSTIP) address this issue. While, convolutional sparse coding (CSC) with the capability to detect an anomaly event by produce more error in the reconstruction, is preferred rather than patch-based. It demonstrates that utilization SSTIP and CSC yields promising performance.

关键词： Video anomaly Selective Spatio-temporal interest point convolutional sparse coding

来源：评论

学校读者我要写书评

暂无评论

convolutional Laplacian sparse coding

Convolutional Laplacian Sparse Coding

引用

IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI)

作者： Luo, Xiyang Wohlberg, Brendt Univ Calif Los Angeles Dept Math Los Angeles CA 90024 USA Los Alamos Natl Lab Div Theoret Los Alamos NM USA

ISBN: (纸本)9781467399197

We propose to extend the the standard convolutional sparse representation by combining it with a non-local graph Laplacian term. This additional term is chosen to address some of the deficiencies of the l(1) norm in regularizing these representations, and is shown to have an advantage in both dictionary learning and an example image reconstruction problem.

关键词： sparse Representation convolutional sparse coding Laplacian sparse coding

来源：评论

学校读者我要写书评

暂无评论

Informed monaural source separation of music based on convolutional sparse coding 40

Informed monaural source separation of music based on convol...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Jao, Ping-Keng Yang, Yi-Hsuan Wohlberg, Brendt Research Center for Information Technology Innovation Academia Sinica Taiwan Theoretical Division Los Alamos National Laboratory United States

ISBN: (纸本)9781467369978

Monaural source separation is a challenging problem that has many important applications in music information retrieval. In this paper, we focus on the score-informed variant of this problem. While non-negative matrix factorization and some other approaches have been shown effective, few existing approaches have properly taken the phase information into account. There are unnatural sound in the separation result, as the phase of each source signal is considered equivalent to the phase of the mixed signal. To remedy this, we propose to perform source separation directly in the time domain using a convolutional sparse coding (CSC) approach. Evaluation on the Bach10 dataset shows that, when the instrument, pitch and onset/offset time are informed, the source to distortion ratio of the separation result reaches 8.59 dB, which is 2.02 dB higher than a state-of-the-art system called Soundprism. © 2015 IEEE.

关键词： convolutional sparse coding dictionary learning score-informed monaural source separation

来源：评论

学校读者我要写书评

暂无评论

Efficient convolutional Forward Modeling and sparse coding in Multichannel Imaging 32

Efficient Convolutional Forward Modeling and Sparse Coding i...

引用

32nd European Signal Processing Conference (EUSIPCO)

作者： Wang, Han Kvich, Yhonatan Perez, Eduardo Roemer, Florian Eldar, Yonina C. Fraunhofer Inst Nondestruct Testing Appl AI Signal Proc & Data Anal Saarbrucken Germany Weizmann Inst Sci Fac Math & Comp Sci Rehovot Israel Tech Univ Ilmenau Dept Elect Measurements & Signal Proc Ilmenau Germany

ISBN: (纸本)9789464593617;9798331519773

This study considers the Block-Toeplitz structural properties inherent in traditional multichannel forward model matrices, using Full Matrix Capture (FMC) in ultrasonic testing as a case study. We propose an analytical convolutional forward model that transforms reflectivity maps into FMC data. Our findings demonstrate that the convolutional model excels over its matrix-based counterpart in terms of computational efficiency and storage requirements. This accelerated forward modeling approach holds significant potential for various inverse problems, notably enhancing sparse Signal Recovery (SSR) within the context LASSO regression, which facilitates efficient convolutional sparse coding (CSC) algorithms. Additionally, we explore the integration of convolutional Neural Networks (CNNs) for the forward model, employing deep unfolding to implement the Learned Block convolutional ISTA (BC-LISTA).

关键词： Forward Modeling convolutional sparse coding Deep Unfolding Toeplitz Matrix Multichannel Imaging

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT convolutional sparse coding

EFFICIENT CONVOLUTIONAL SPARSE CODING

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Wohlberg, Brendt Los Alamos Natl Lab Div Theoret Los Alamos NM 87545 USA

ISBN: (纸本)9781479928934

When applying sparse representation techniques to images, the standard approach is to independently compute the representations for a set of overlapping image patches. This method performs very well in a variety of applications, but the independent sparse coding of each patch results in a representation that is not optimal for the image as a whole. A recent development is convolutional sparse coding, in which a sparse representation for an entire image is computed by replacing the linear combination of a set of dictionary vectors by the sum of a set of convolutions with dictionary filters. A disadvantage of this formulation is its computational expense, but the development of efficient algorithms has received some attention in the literature, with the current leading method exploiting a Fourier domain approach. The present paper introduces a new way of solving the problem in the Fourier domain, leading to substantially reduced computational cost.

关键词： sparse Representation sparse coding convolutional sparse coding ADMM

来源：评论

学校读者我要写书评

暂无评论

MDSC-Net: Multi-Modal Discriminative sparse coding Driven RGB-D Classification Network

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 442-454页

作者： Xu, Jingyi Deng, Xin Fu, Yibing Xu, Mai Li, Shengxi Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Beihang Univ Shen Yuan Honors Coll Beijing 100191 Peoples R China

In this paper, we propose a novel sparsity-driven deep neural network to solve the RGB-D image classification problem. Different from existing classification networks, our network architecture is designed by drawing inspirations from a new proposed multi-modal discriminative sparse coding (MDSC) model. The key feature of this model is that it can gradually separate the discriminative and non-discriminative features in RGB-D images in a coarse-to-fine manner. Only the discriminative features are integrated and refined for classification, while the non-discriminative features are discarded, to improve the classification accuracy and efficiency. Derived from the MDSC model, the proposed network is composed of three modules, i.e., the shared feature extraction (SFE) module, discriminative feature refinement (DFR) module, and classification module. The architecture of each module is derived from the optimization solution in the MDSC model. To the best of our knowledge, this is the first time a fully sparsity-driven network has been proposed for RGB-D image classification. Extensive results verify the effectiveness of our method on different RGB-D image datasets.

关键词： Feature extraction Image coding Image classification Dictionaries Optimization Classification algorithms Deep learning convolutional neural networks Accuracy Encoding convolutional sparse coding RGB-D image classification Discriminative features

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for pose error prediction in parallel robots

引用

MEASUREMENT 2025年第PartA期242卷

作者： Zhang, Han Zhu, Xin Yang, Ming Liu, Zhihua Cai, Chenguang Natl Inst Metrol Inst Mech & Acoust Beijing 100029 Peoples R China Guizhou Univ Coll Elect Engn Guiyang 550025 Peoples R China

Parallel robots are increasingly favored in industrial automation due to their high precision, stability, and rigidity in high-speed and heavy-load tasks. However, factors such as manufacturing tolerances, assembly deviations, loads, and environmental conditions can lead to pose inaccuracies, manifesting as both geometric and non-geometric errors. Traditional model-driven approaches effectively predict geometric errors but often neglect non-geometric factors, potentially impacting the overall accuracy. This paper presents a deep learning-based method for comprehensive pose error prediction in parallel robots, addressing both geometric and non-geometric errors. The proposed approach employs an encoder-decoder network that takes target pose inputs and outputs predicted pose errors. The encoder integrates multi-layer convolutional sparse coding (CSC) blocks and efficient channel attention (ECA) modules to extract features from the network inputs. Monte Carlo dropout is utilized to estimate prediction uncertainties, enhancing the reliability of the network predictions. Experimental validation on a Stewart platform demonstrates the high accuracy and robustness of the method under various loading conditions. Comparative analyses with several typical models affirm the superior performance of the proposed network, indicating its potential to improve the operational accuracy and reliability of parallel robots in high-precision applications.

关键词： Parallel robots Pose error prediction Deep learning convolutional sparse coding Monte Carlo dropout

来源：评论

学校读者我要写书评

暂无评论

Learning to Generalize Heterogeneous Representation for Cross-Modality Image Synthesis via Multiple Domain Interventions

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年 1-22页

作者： Huang, Yawen Huang, Huimin Zheng, Hao Li, Yuexiang Zheng, Feng Zhen, Xiantong Zheng, Yefeng Tencent Jarvis Res Ctr YouTu Lab Shenzhen Peoples R China Guangxi Med Univ Guangxi Key Lab Genom & Personalized Med Med AI Res MARS Grp Nanning 530021 Guangxi Peoples R China Southern Univ Sci & Technol Shenzhen Peoples R China United Imaging Healthcare Co Ltd Cent Res Inst Beijing Peoples R China Westlake Univ Med Artificial Intelligence Lab Hangzhou Peoples R China

Magnetic resonance imaging with modality diversity substantially increases productivity in routine diagnosis and advanced research. However, high inter-equipment variability and expensive examination cost remain as key challenges in acquiring and utilizing multi-modal images. Missing modalities often can be synthesized from existing ones. While the rapid growth in image style transfer with deep models overwhelms the above endeavor, such image synthesis may not always be achievable and even impractical when applied to medical data. The proposed method addresses this issue by a convolutional sparse coding (CSC) adaptation network to handle the lacking of generalizing medical image representation learning. We reduce both inter-domain and intra-domain divergences by the domain-adaptation and domain-standardization modules, respectively. On the basis of CSC features, we penalize their subspace mismatching to reduce the generalization error. The overall framework is cast in a minimax setting, and the extensive experiments show that the proposed method yields state-of-the-art results on multiple datasets.

关键词： Representation learning Cross-moality images convolutional sparse coding Image synthesis

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：