Match!

Multiple Kernel Sparse Representations for Supervised and Unsupervised Learning

Published on Jul 1, 2014in IEEE Transactions on Image Processing6.79
· DOI :10.1109/TIP.2014.2322938
Jayaraman J. Thiagarajan10
Estimated H-index: 10
(ASU: Arizona State University),
Karthikeyan Natesan Ramamurthy12
Estimated H-index: 12
(ASU: Arizona State University),
Andreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
Cite
Abstract
In complex visual recognition tasks, it is typical to adopt multiple descriptors, which describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a unified feature space in a principled manner using kernel methods. Sparse models that generalize well to the test data can be learned in the unified kernel space, and appropriate constraints can be incorporated for application in supervised and unsupervised learning. In this paper, we propose to perform sparse coding and dictionary learning in the multiple kernel space, where the weights of the ensemble kernel are tuned based on graph-embedding principles such that class discrimination is maximized. In our proposed algorithm, dictionaries are inferred using multiple levels of 1D subspace clustering in the kernel space, and the sparse codes are obtained using a simple levelwise pursuit scheme. Empirical results for object recognition and image clustering show that our algorithm outperforms existing sparse coding based approaches, and compares favorably to other state-of-the-art methods.
  • References (84)
  • Citations (45)
Cite
References84
Newest
Published on Dec 1, 2013in IEEE Transactions on Image Processing6.79
Hien Van Nguyen15
Estimated H-index: 15
(Princeton University),
Vishal M. Patel34
Estimated H-index: 34
(UMD: University of Maryland, College Park)
+ 1 AuthorsRama Chellappa88
Estimated H-index: 88
(UMD: University of Maryland, College Park)
In this paper, we present dictionary learning methods for sparse signal representations in a high dimensional feature space. Using the kernel method, we describe how the well known dictionary learning approaches, such as the method of optimal directions and KSVD, can be made nonlinear. We analyze their kernel constructions and demonstrate their effectiveness through several experiments on classification problems. It is shown that nonlinear dictionary learning approaches can provide significantly...
Published on May 1, 2013 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
Yin Zhou7
Estimated H-index: 7
(UD: University of Delaware),
Jinglun Gao2
Estimated H-index: 2
(UD: University of Delaware),
Kenneth E. Barner32
Estimated H-index: 32
(UD: University of Delaware)
Discovering the intrinsic low-dimensional structure from high-dimensional observation space (e.g., images, videos), in many cases, is critical to successful recognition. However, many existing nonlinear manifold learning (NML) algorithms have quadratic or cubic complexity in the number of data, which makes these algorithms computationally exorbitant in processing real-world large-scale datasets. Randomly selecting a subset of data points is very likely to place NML algorithms at the risk of loca...
Published on May 1, 2013 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
Rushil Anirudh5
Estimated H-index: 5
(ASU: Arizona State University),
Karthikeyan Natesan Ramamurthy12
Estimated H-index: 12
(ASU: Arizona State University)
+ 2 AuthorsAndreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
In this paper, we consider low-dimensional and sparse representation models for human actions, that are consistent with how actions evolve in high-dimensional feature spaces. We first show that human actions can be well approximated by piecewise linear structures in the feature space. Based on this, we propose a new dictionary model that considers each atom in the dictionary to be an affine subspace defined by a point and a corresponding line. When compared to centered clustering approaches such...
Jayaraman J. Thiagarajan10
Estimated H-index: 10
,
Karthikeyan Natesan Ramamurthy12
Estimated H-index: 12
,
Andreas Spanias26
Estimated H-index: 26
Sparse representations using learned dictionaries are being increasingly used with success in several data processing and machine learning applications. The availability of abundant training data necessitates the development of efficient, robust and provably good dictionary learning algorithms. Algorithmic stability and generalization are desirable characteristics for dictionary learning algorithms that aim to build global dictionaries which can efficiently model any test data similar to the tra...
Published on Jan 1, 2013
Jayaraman J. Thiagarajan10
Estimated H-index: 10
(ASU: Arizona State University),
Karthikeyan Natesan Ramamurthy12
Estimated H-index: 12
(ASU: Arizona State University),
Andreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
Dictionaries adapted to the data provide superior performance when compared to predefined dictionaries in applications involving sparse representations. Algorithmic stability and generalization are desirable characteristics for dictionary learning algorithms that aim to build global dictionaries which can efficiently model any test data similar to the training samples. In this paper, we propose an algorithm to learn dictionaries for sparse representation of image patches, and prove that the prop...
Published on Jan 1, 2013in Digital Signal Processing2.79
Jayaraman J. Thiagarajan10
Estimated H-index: 10
(ASU: Arizona State University),
Karthikeyan Natesan Ramamurthy12
Estimated H-index: 12
(ASU: Arizona State University),
Andreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
Mixing matrix estimation in instantaneous blind source separation (BSS) can be performed by exploiting the sparsity and disjoint orthogonality of source signals. As a result, approaches for estimating the unknown mixing process typically employ clustering algorithms on the mixtures in a parametric domain, where the signals can be sparsely represented. In this paper, we propose two algorithms to perform discriminative clustering of the mixture signals for estimating the mixing matrix. For the cas...
Published on Nov 1, 2012
Karthikeyan Natesan Ramamurthy12
Estimated H-index: 12
(ASU: Arizona State University),
Jayaraman J. Thiagarajan10
Estimated H-index: 10
(ASU: Arizona State University)
+ 1 AuthorsAndreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
Several supervised, semi-supervised, and unsupervised machine learning schemes can be unified under the general framework of graph embedding. Incorporating graph embedding principles into sparse representation based learning schemes can provide an improved performance in several learning tasks. In this work, we propose a dictionary learning procedure for computing discriminative sparse codes that obey graph embedding constraints. In order to compute the graph-embedded sparse codes, we integrate ...
Published on Nov 1, 2012 in BIBE (Bioinformatics and Bioengineering)
Jayaraman J. Thiagarajan10
Estimated H-index: 10
(ASU: Arizona State University),
Deepta Rajan4
Estimated H-index: 4
(ASU: Arizona State University)
+ 2 AuthorsAndreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
In this paper, we describe a pixel based approach for automated segmentation of tumor components from MR images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. Since it is trivial to obtain sparse codes for pixel values, we propose to consider their non-linear similarities to perform kernel sparse coding in a high dimensional feature space. We develop the kernel K-lines clustering procedure for inferring kernel dictionar...
Published on Oct 7, 2012 in ECCV (European Conference on Computer Vision)
Hanlin Goh9
Estimated H-index: 9
(Agency for Science, Technology and Research),
Nicolas Thome22
Estimated H-index: 22
(University of Paris)
+ 1 AuthorsJoo-Hwee Lim24
Estimated H-index: 24
(Agency for Science, Technology and Research)
Recently, the coding of local features (e.g. SIFT) for image categorization tasks has been extensively studied. Incorporated within the Bag of Words (BoW) framework, these techniques optimize the projection of local features into the visual codebook, leading to state-of-the-art performances in many benchmark datasets. In this work, we propose a novel visual codebook learning approach using the restricted Boltzmann machine (RBM) as our generative model. Our contribution is three-fold. Firstly, we...
Published on Sep 1, 2012 in ICIP (International Conference on Image Processing)
Jayaraman J. Thiagarajan10
Estimated H-index: 10
(ASU: Arizona State University),
Karthikeyan Natesan Ramamurthy12
Estimated H-index: 12
(ASU: Arizona State University)
+ 1 AuthorsAndreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
The success of sparse representations in image modeling and recovery has motivated its use in computer vision applications. Image retrieval and classification tasks require extracting features that discriminate different image classes. State-of-the-art object recognition methods based on sparse coding use spatial pyramid features obtained from dense descriptors. In this paper, we develop a feature extraction method that uses multiple global/local features extracted from large overlapping regions...
Cited By45
Newest
Published on Apr 9, 2019in Multidimensional Systems and Signal Processing2.34
Fatemeh Taibi (Shahid Chamran University of Ahvaz), Gholamreza Akbarizadeh10
Estimated H-index: 10
(Shahid Chamran University of Ahvaz),
Ebrahim Farshidi8
Estimated H-index: 8
(Shahid Chamran University of Ahvaz)
In this paper, the main goal is to identify the sine fractures of reservoir rock automatically. Therefore, a five-step algorithm is applied on the imaging logs. The first step consists of extracting the features of the imaging log by applying the Zernike moments. In the second step, the features are learned by using sparse coding. In the third step, the imaging log is segmented by using the self-organizing map neural network and the training dataset. In the fourth step, the fracture points are e...
Li Shang6
Estimated H-index: 6
,
Yan Zhou2
Estimated H-index: 2
,
Zhan-Li Sun6
Estimated H-index: 6
(Anda: Anhui University)
To extract the essential features from a relatively small number of sampling set and further improve the feature recognition precision of images, a novel palm recognition method using the adaptive lifting wavelet transform (ALWT) based sparse representation (SR) algorithm is proposed here. This lifting wavelet behaves local texture features in spatial and the fast operation speed. While SR method can effectively represent structure features of images and behaves adaptive denoising characteristic...
Published on Aug 1, 2019in Medical Image Analysis8.88
Euijoon Ahn7
Estimated H-index: 7
(USYD: University of Sydney),
Ashnil Kumar10
Estimated H-index: 10
(USYD: University of Sydney)
+ 2 AuthorsJinman Kim16
Estimated H-index: 16
(USYD: University of Sydney)
Abstract The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analysis problems. Such supervised approaches, however, are difficult to implement in the medical domain where large volumes of labelled data are difficult to obtain due to the complexity of manual annotation and inter- and intra-observer variability in label assignment. We pr...
Published on Jul 1, 2019in Pattern Recognition5.90
Jianqiang Song (Xidian University), Xuemei Xie10
Estimated H-index: 10
(Xidian University)
+ 1 AuthorsWeisheng Dong18
Estimated H-index: 18
(Xidian University)
Abstract Discriminative dictionary learning (DDL) has demonstrated significantly improved performance for image classification. However, most of the existing DDL methods just adopt the single-layer dictionary learning architecture, which narrows the discriminative ability of the coding vectors. Another limitation of these methods is that the atoms of the learned dictionary are easily affected by the noise in the original data. To this end, a powerful architecture, called the multi-layer discrimi...
Published on Jan 1, 2019
Niharika Shimona D’Souza1
Estimated H-index: 1
,
Mary Beth Nebel19
Estimated H-index: 19
+ 2 AuthorsArchana Venkataraman9
Estimated H-index: 9
The problem of linking functional connectomics to behavior is extremely challenging due to the complex interactions between the two distinct, but related, data domains. We propose a coupled manifold optimization framework which projects fMRI data onto a low dimensional matrix manifold common to the cohort. The patient specific loadings simultaneously map onto a behavioral measure of interest via a second, non-linear, manifold. By leveraging the kernel trick, we can optimize over a potentially in...
Published on Apr 1, 2019in Pattern Recognition5.90
Xiaoning Song10
Estimated H-index: 10
(Jiangnan University),
Youming Chen (Jiangnan University)+ 3 AuthorsXiaojun Wu18
Estimated H-index: 18
(Jiangnan University)
Abstract Traditional collaborative representation based classification (CRC) method usually faces the challenge of data uncertainty hence results in poor performance, especially in the presence of appearance variations in pose, expression and illumination. To overcome this issue, this paper presents a CRC-based face classification method by jointly using block weighted LBP and analysis dictionary learning. To this end, we first design a block weighted LBP histogram algorithm to form a set of loc...
Published on Apr 1, 2019 in SMC (Systems, Man and Cybernetics)
Liu Huaping24
Estimated H-index: 24
(THU: Tsinghua University),
He Liu1
Estimated H-index: 1
(THU: Tsinghua University)
+ 1 AuthorsBin Fang6
Estimated H-index: 6
(THU: Tsinghua University)
For most sparse coding methods, data samples are first encoded as hand-crafted features, followed by another separate learning step that generates dictionary and sparse codes. However, such feature representations may not be optimally compatible with the learning process, thus producing suboptimal results. In this paper, we propose a new architecture for nonlinear dictionary learning with sparse coding, in which samples are mapped into sparse codes via carefully designed stacked auto-encoder (SA...
Published on Feb 13, 2019in Sensors3.03
Liang Shi , Xiaoning Song10
Estimated H-index: 10
+ 1 AuthorsYuquan Zhu
Traditional Collaborative Representation-based Classification algorithms for face recognition (CRC) usually suffer from data uncertainty, especially if it includes various poses and illuminations. To address this issue, in this paper, we design a new CRC method using histogram statistical measurement (H-CRC) combined with a 3D morphable model (3DMM) for pose-invariant face classification. First, we fit a 3DMM to raw images in the dictionary to reconstruct the 3D shapes and textures. The fitting ...
Euijoon Ahn7
Estimated H-index: 7
,
Ashnil Kumar10
Estimated H-index: 10
+ 2 AuthorsJinman Kim16
Estimated H-index: 16
(USYD: University of Sydney)
Medical image analysis using supervised deep learning methods remains problematic because of the reliance of deep learning methods on large amounts of labelled training data. Although medical imaging data repositories continue to expand there has not been a commensurate increase in the amount of annotated data. Hence, we propose a new unsupervised feature learning method that learns feature representations to then differentiate dissimilar medical images using an ensemble of different convolution...
Published on Dec 1, 2018in Applied and Computational Harmonic Analysis2.96
Abhishake (IITD: Indian Institute of Technology Delhi), S. Sivananthan (IITD: Indian Institute of Technology Delhi)
Abstract In this paper, we study the Nystrom type subsampling for large-scale kernel methods to reduce the computational complexities of big data. We discuss the multi-penalty regularization scheme based on Nystrom type subsampling which is motivated from well-studied manifold regularization schemes. We develop a theoretical analysis of the multi-penalty least-square regularization scheme under the general source condition in vector-valued function setting, therefore the results can also be appl...