scispace - formally typeset
Search or ask a question
Topic

Sparse approximation

About: Sparse approximation is a research topic. Over the lifetime, 18037 publications have been published within this topic receiving 497739 citations. The topic is also known as: Sparse approximation.


Papers
More filters
Proceedings ArticleDOI
01 Jul 2017
TL;DR: This work introduces additional gate variables to perform parameter selection and shows that this is equivalent to using a spike-and-slab prior, and experimentally validate the method on both small and large networks which result in highly sparse neural network models.
Abstract: The emergence of Deep neural networks has seen human-level performance on large scale computer vision tasks such as image classification. However these deep networks typically contain large amount of parameters due to dense matrix multiplications and convolutions. As a result, these architectures are highly memory intensive, making them less suitable for embedded vision applications. Sparse Computations are known to be much more memory efficient. In this work, we train and build neural networks which implicitly use sparse computations. We introduce additional gate variables to perform parameter selection and show that this is equivalent to using a spike-and-slab prior. We experimentally validate our method on both small and large networks which result in highly sparse neural network models.

159 citations

Proceedings ArticleDOI
23 Jun 2014
TL;DR: This paper proposes a new joint sparse representation model for robust feature-level fusion in multi-cue visual tracking and dynamically removes unreliable features to be fused for tracking by using the advantages of sparse representation.
Abstract: The use of multiple features for tracking has been proved as an effective approach because limitation of each feature could be compensated. Since different types of variations such as illumination, occlusion and pose may happen in a video sequence, especially long sequence videos, how to dynamically select the appropriate features is one of the key problems in this approach. To address this issue in multicue visual tracking, this paper proposes a new joint sparse representation model for robust feature-level fusion. The proposed method dynamically removes unreliable features to be fused for tracking by using the advantages of sparse representation. As a result, robust tracking performance is obtained. Experimental results on publicly available videos show that the proposed method outperforms both existing sparse representation based and fusion-based trackers.

159 citations

Journal ArticleDOI
TL;DR: A novel data-driven fault diagnosis method based on sparse representation and shift-invariant dictionary learning is proposed, which proves the effectiveness and robustness of the proposed method and the comparison with the state-of-the-art method is illustrated.
Abstract: It is always a primary challenge in fault diagnosis of a wind turbine generator to extract fault character information under strong noise and nonstationary condition. As a novel signal processing method, sparse representation shows excellent performance in time–frequency analysis and feature extraction. However, its result is directly influenced by dictionary, whose atoms should be as similar with signal's inner structure as possible. Due to the variability of operation environment and physical structure in industrial systems, the patterns of impulse signals are changing over time, which makes creating a proper dictionary even harder. To solve the problem, a novel data-driven fault diagnosis method based on sparse representation and shift-invariant dictionary learning is proposed. The impulse signals at different locations with the same characteristic can be represented by only one atom through shift operation. Then, the shift-invariant dictionary is generated by taking all the possible shifts of a few short atoms and, consequently, is more applicable to represent long signals that in the same pattern appear periodically. Based on the learnt shift-invariant dictionary, the coefficients obtained can be sparser, with the extracted impulse signal being closer to the real signal. Finally, the time–frequency representation of the impulse component is obtained with consideration of both the Wigner–Ville distribution of every atom and the corresponding sparse coefficient. The excellent performance of different fault diagnoses in a fault simulator and a wind turbine proves the effectiveness and robustness of the proposed method. Meanwhile, the comparison with the state-of-the-art method is illustrated, which highlights the superiority of the proposed method.

159 citations

BookDOI
01 Jan 1972
TL;DR: The Role of Partitioning in the Numerical Solution of Sparse Systems and several Strategies for Reducing the Bandwidth of Matrices are discussed.
Abstract: Symposium on Sparse Matrices and Their Applications.- Computational Circuit Design.- Eigenvalue Methods for Sparse Matrices.- Sparse Matrix Approach to the Frequency Domain Analysis of Linear Passive Electrical Networks.- Some Basic Technqiues for Solving Sparse Systems of Linear Equations.- Vector and Matrix Variability Type in Sparse Matrix Algorithms.- Linear Programming.- The Partitioned Preassigned Pivot Procedure (P4).- Modifying Triangular Factors of the Basis in the Simplex Method.- Partial Differential Equations.- A New Iterative Procedure for the Solution of Sparse Systems of Linear Difference Equations.- Block Eliminations on Finite Element Systems of Equations.- Application of the Finite Element Method to Regional Water Transport Phenomena.- On the Use of Fast Methods for Separable Finite Difference Equations for the Solution of General Elliptic Problems.- Special Topics.- Application of Sparse Matrices to Analytical Photogrammetry.- Generalized View of a Data Base.- Combinatorics and Graph Theory.- Several Strategies for Reducing the Bandwidth of Matrices.- GRAAL - A Graph Algorithmic Language.- The Role of Partitioning in the Numerical Solution of Sparse Systems.

159 citations

Proceedings ArticleDOI
30 May 1999
TL;DR: This paper uses frames designed by MOD in a multiframe compression (MFC) scheme to apply to ECG signals, and demonstrates improved rate-distortion performance by 1-4 dB, and that variable sized frames perform better than fixed sized frames.
Abstract: The method of optimal directions (MOD) is an iterative method for designing frames for sparse representation purposes using a training set. In this paper we use frames designed by MOD in a multiframe compression (MFC) scheme. Both the MOD and the MFC need a vector selection algorithm, and orthogonal matching pursuit (OMP) is used in this paper. In the MFC scheme several different frames are used, each optimized for a fixed number of selected frame vectors in each approximation. We apply the MOD and the MFC scheme to ECG signals, and do experiments with both fixed size and variable size on the different frames used in the MFC scheme. Compared to traditional transform based compression, the experiments demonstrate improved rate-distortion performance by 1-4 dB, and that variable sized frames perform better than fixed sized frames.

158 citations


Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
93% related
Image segmentation
79.6K papers, 1.8M citations
92% related
Convolutional neural network
74.7K papers, 2M citations
92% related
Deep learning
79.8K papers, 2.1M citations
90% related
Image processing
229.9K papers, 3.5M citations
89% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023193
2022454
2021641
2020924
20191,208
20181,371