检索结果-内蒙古大学图书馆

Scalable Online convolutional sparse coding

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

Spatial-spectral feature based approach towards convolutional sparse coding of hyperspectral images

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2019年 188卷 102797-000页

作者： Arun, P., V Mohan, Krishna B. Porwal, A. Indian Inst Technol CSRE Mumbai 400076 Maharashtra India

The sparse coding approaches, which learn over-complete bases for efficiently representing a given set of data, are being extensively studied for various image analysis tasks. However, since sparse analysis of individual bands does not consider inter-spectral characteristics, adaptation of these approaches to hyperspectral domain has been quite limited. In this regard, we investigate convolutional frameworks for simultaneously learning sparse codes and dictionaries so as to efficiently represent the spectral-spatial characteristics of hypercubes. This study also reviews prominent convolutional sparse coding algorithms relevant to hyperspectral datasets. Unlike conventional approaches, in order to address the issues due to huge spectral dimension and high inter-band correlation, the proposed approaches implement sparse coding in a convolutional encoder- decoder framework. Two architectures, one based on shrinkage thresholding algorithm and other based on structured sparse regularization, are proposed. These architectures adopt 3D convolutions in such a way as to model both spectral and spatial features. Although Architecture-1 gives better results than other prominent approaches, its accuracy deteriorates with increase in spectral dimension of input. This can be attributed to the bottleneck due to shrinkage thresholding operation. To address the issue, Architecture-2 adopts structured sparse regularizations over filter weights and feature tensors. Results indicate that the proposed approaches achieve significant improvement in reconstruction accuracy when compared to the existing approaches. The frameworks are also evaluated with respect to super-resolution and dimensionality reduction of hyperspectral datasets. From different experiments, it is observed that the simultaneous usage of 3D and 2D filters along with sparse regularizations significantly improve learning capability of the networks.

关键词： convolutional sparse coding Hyperspectral convolutional neural network

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

convolutional sparse coding with periodic overlapped group sparsity for rolling element bearing fault diagnosis

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2018年第11期29卷 115103-115103页

作者： Xia, Yi Lu, Siliang Univ Anhui Dept Elect Engn & Automat Hefei 230601 Anhui Peoples R China

To cope with the problem of detecting periodic impulses in rotating machines with certain bearing faults, this paper proposes a novel data-driven dictionary learning and sparse coding algorithm. In our approach, the signal is decomposed into one or several components with each one as a convolution of one atom with a sparse activation vector. This manner of signal decomposition is formulated as a convex problem subject to a constraint that the activation vector should have a structure with periodic group sparsity. The solution to such a problem is an alternative optimizing process, that is, with a given dictionary, a sparse coding problem is solved by a split variable augmented Lagrangian shrinkage algorithm (SALSA), and for a fixed activation vector, the dictionary updating is implemented by solving Lagrange dual problem. The advantages of the proposed model over several other approaches are demonstrated by the experiments on both simulated and real vibration signals. The experimental results indicate that the proposed method can effectively detect and extract the latent weak fault impulses even in the presence of heavy noise

关键词： fault diagnosis convolutional sparse coding dictionary learning group sparsity

来源：评论

学校读者我要写书评

暂无评论

PROJECTING ONTO THE MULTI-LAYER convolutional sparse coding MODEL

PROJECTING ONTO THE MULTI-LAYER CONVOLUTIONAL SPARSE CODING ...

引用

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

作者： Sulam, Jeremias Papyan, Vardan Romano, Yaniv Elad, Michael Technion Israel Inst Technol Comp Sci Dept Haifa Israel Technion Israel Inst Technol Elect Engn Dept Haifa Israel

ISBN: (纸本)9781538646588

The recently proposed Multi-Layer convolutional sparse coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of convolutional Neural Networks (CNNs). Under this framework, the forward pass in a CNN is equivalent to an algorithm that estimates nested sparse representation vectors from a given input signal. Despite having served as a pivotal connection between CNNs and sparse modeling, it is still unclear how to develop pursuit algorithms that serve this model exactly. In this work, we propose a new pursuit formulation by adopting a projection approach. We provide new and improved bounds on the stability of the resulting convolutional sparse representations, and we propose a multi-layer projection algorithm to retrieve them. We demonstrate this algorithm numerically, showing that it is superior to the Layered Basis Pursuit alternative in retrieving the representations of signals belonging to the ML-CSC model.

关键词： convolutional sparse coding Multi-layer Pursuit Stability Guarantees convolutional Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Single Image Super-resolution Based on Residual Learning and convolutional sparse coding 10

Single Image Super-resolution Based on Residual Learning and...

引用

10th International Conference on Digital Image Processing (ICDIP)

作者： Xie, Chao Jiang, Shengqin Lu, Xiaobo Southeast Univ Sch Automat Nanjing 210096 Jiangsu Peoples R China Minist Educ Key Lab Measurement & Control Complex Syst Engn Nanjing 210096 Jiangsu Peoples R China

ISBN: (数字)9781510622005

ISBN: (纸本)9781510622005

In this paper, we propose an improved method for single image super-resolution on the basis of residual learning and convolutional sparse coding (CSC). The key idea of it is to first perform a CSC-based decomposition on the input so that it can be split into two predefined parts: the smooth and residual components. Then, the extracted components are individually mapped according to their own characteristics, rather than directly perform a mapping from the original input. Specifically, we place more emphases on the residual one as it is much important to our task, while the smooth one is just propagated to the final output for providing a quick reference. Accordingly, the final architecture of our method conceptually integrates all the above steps into a completely end-to-end trainable deep network. Extensive experimental results indicate that our proposed method outperforms many state-of-the-art methods in terms of both visual fidelity and objective evaluation.

关键词： Single image super-resolution residual learning deep convolutional neural networks convolutional sparse coding

来源：评论

学校读者我要写书评

暂无评论

DATA DRIVEN convolutional sparse coding FOR VISUAL RECOGNITION

DATA DRIVEN CONVOLUTIONAL SPARSE CODING FOR VISUAL RECOGNITI...

引用

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

作者： Zeng, Yijie Chen, Jichao Huang, Guang-Bin Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

ISBN: (纸本)9781538646588

convolutional sparse coding (CSC) has become an important method in image processing and computer vision. In this paper we focus on visual recognition problems and apply CSC as a feature learning method. We propose a task-specific approach to treat the dictionary of CSC as parameters for a larger learning framework. These parameters are differentiable under mild conditions, and could be updated end-to-end using back-propagation when the errors from the task objectives are provided. We perform several experiments to show that such method provides a more discriminate representation compared with previous CSC methods, and this data driven approach is effective for visual recognition problems.

关键词： convolutional sparse coding dictionary learning sparse representation supervised learning visual recognition

来源：评论

学校读者我要写书评

暂无评论

A Fast Parallel Algorithm for convolutional sparse coding 13

A Fast Parallel Algorithm for Convolutional Sparse Coding

引用

13th IEEE Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)

作者： Skau, Erik Wohlberg, Brendt Los Alamos Natl Lab CCS Div CCS-3 T-5 Los Alamos NM 87544 USA Los Alamos Natl Lab Div T CCS-3 T-5 Los Alamos NM 87544 USA Los Alamos Natl Lab Div T T-5 Los Alamos NM 87545 USA

ISBN: (纸本)9781538609514

The current leading algorithms for convolutional sparse coding are not inherently parallelizable, and therefore are not able to fully exploit modern multi-core architectures. We address this deficiency by developing a new algorithm that partitions the dictionary and the corresponding coefficient maps into groups, solving the main subproblems for all of the groups in parallel. Theoretical complexities and implementational details are discussed and validated with computational experiments, which indicate speed improvements by about a factor of 5, depending on the specific problem.

关键词： convolutional sparse Representations convolutional sparse coding ADMM

来源：评论

学校读者我要写书评

暂无评论

Adaptive convolutional sparse coding with Weighted l1 Norm

Adaptive Convolutional Sparse Coding with Weighted l1 Norm

引用

第三十八届中国控制会议

作者： Jiale Qiu Min Yang College Of Automation & College Of Artificial Intelligence Nanjing University of Posts and Telecommunications

convolutional sparse coding computes a sparse representation for an entire image by modeling the signal as a sum of several convolutions of dictionary filters and sparse feature maps, instead of the linear combination of dictionary vectors in standard sparse coding. Most of the existing algorithms use a invariant regularization parameter, which can hardly deal well with varying local contrast. In this paper, we propose a new method Adaptive convolutional sparse coding(ACSC) by introducing a set of weight vectors into the 1 regularization term to set different penalty coefficients for different sparse feature maps, which can better adapt with the varying local sparse requirements of images. Experimental results show that the proposed ACSC is superior to the existing convolutional sparse coding algorithm in image reconstruction.

关键词： sparse coding convolutional sparse coding ADMM Image Reconstruction

来源：评论

学校读者我要写书评

暂无评论

LEARNED convolutional sparse coding

LEARNED CONVOLUTIONAL SPARSE CODING

引用

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

作者： Sreter, Hillel Giryes, Raja Tel Aviv Univ Sch Elect Engn Tel Aviv Israel

ISBN: (纸本)9781538646588

We propose a convolutional recurrent sparse auto-encoder model. The model consists of a sparse encoder, which is a convolutional extension of the learned ISTA (LISTA) method, and a linear convolutional decoder. Our strategy offers a simple strategy for learning a task-driven sparse convolutional dictionary (CD), and producing an approximate convolutional sparse code (CSC) over the learned dictionary. We trained the model to minimize reconstruction loss via gradient decent with back-propagation and have achieved competitve results to KSVD image denoising and to leading CSC methods in image inpainting requiring only a small fraction of their runtime.

关键词： sparse coding ISTA LISTA convolutional sparse coding Neural networks

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：