Scalable linear visual feature learning via online parallel nonnegative matrix factorization
Files
(Restricted Access)
Date
2016
Authors
Zhao, X.
Li, X.
Zhang, Z.
Shen, C.
Zhuang, Y.
Gao, L.
Li, X.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
IEEE Transactions on Neural Networks and Learning Systems, 2016; 27(12):2628-2642
Statement of Responsibility
Xueyi Zhao, Xi Li, Zhongfei Zhang, Chunhua Shen, Yueting Zhuang, Lixin Gao and Xuelong Li
Conference Name
Abstract
Visual feature learning, which aims to construct an effective feature representation for visual data, has a wide range of applications in computer vision. It is often posed as a problem of nonnegative matrix factorization (NMF), which constructs a linear representation for the data. Although NMF is typically parallelized for efficiency, traditional parallelization methods suffer from either an expensive computation or a high runtime memory usage. To alleviate this problem, we propose a parallel NMF method called alternating least square block decomposition (ALSD), which efficiently solves a set of conditionally independent optimization subproblems based on a highly parallelized fine-grained grid-based blockwise matrix decomposition. By assigning each block optimization subproblem to an individual computing node, ALSD can be effectively implemented in a MapReduce-based Hadoop framework. In order to cope with dynamically varying visual data, we further present an incremental version of ALSD, which is able to incrementally update the NMF solution with a low computational cost. Experimental results demonstrate the efficiency and scalability of the proposed methods as well as their applications to image clustering and image retrieval.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.