Learning compact binary codes from higher-order tensors via Free-Form Reshaping and Binarized Multilinear PCA

Haiping LU, Jianxin Wu, Yu Zhang

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

For big, high-dimensional dense features, it is important to learn compact binary codes or compress them for greater memory efficiency. This paper proposes a Binarized Multilinear PCA (BMP) method for this problem with Free-Form Reshaping (FFR) of such features to higher-order tensors, lifting the structure-modelling restriction in traditional tensor models. The reshaped tensors are transformed to a subspace using multilinear PCA. Then, we unsupervisedly select features and supervisedly binarize them with a minimum-classification-error scheme to get compact binary codes. We evaluate BMP on two scene recognition datasets against state-of-the-art algorithms. The FFR works well in experiments. With the same number of compression parameters (model size), BMP has much higher classification accuracy. To achieve the same accuracy or compression ratio, BMP has an order of magnitude smaller number of compression parameters. Thus, BMP has great potential in memory-sensitive applications such as mobile computing and big data analytics.

Original languageEnglish
Title of host publication2016 International Joint Conference on Neural Networks, IJCNN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3008-3015
Number of pages8
ISBN (Electronic)9781509006199
DOIs
Publication statusPublished - 31 Oct 2016
Event2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada
Duration: 24 Jul 201629 Jul 2016

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2016-October

Conference

Conference2016 International Joint Conference on Neural Networks, IJCNN 2016
Country/TerritoryCanada
CityVancouver
Period24/07/1629/07/16

Scopus Subject Areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Learning compact binary codes from higher-order tensors via Free-Form Reshaping and Binarized Multilinear PCA'. Together they form a unique fingerprint.

Cite this