skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Tensorized Feature Spaces for Feature Explosion

Abstract

In this paper 1 1 This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-000R22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan) This research used resources of the Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC05-000R22725., we present a novel framework that uses tensor factorization to generate richer feature spaces for pixel classification in hyperspectral images. In particular, we assess the performance of different tensor rank decomposition methods as compared to the traditional kernel-based approaches for the hyperspectral image classification problem. We propose Orion, which takes as input a hyperspectral image tensor and a rank and outputs an enhanced feature space from the factor matrices of the decomposed tensor. Our method is a feature explosion technique thatmore » inherently maps low dimensional input space in $$\mathbb{R}^{K}$$ to high dimensional space in $$\mathbb{R}^{R}$$ , where $$R\gg K$$ , say in the order of 1000x, like a kernel. We show how the proposed method exploits the multi-linear structure of hyperspectral three dimensional tensor. We demonstrate the effectiveness of our method with experiments on three publicly available hyperspectral datasets with labeled pixels and compare their classification performance against traditional linear and non-linear supervised learning methods such as SVM with Linear, Polynomial, RBF kernels, and the Multi-Layer Perceptron model. Finally, we explore the relationship between the rank of the tensor decomposition and the classification accuracy using several hyperspectral datasets with ground truth.« less

Authors:
 [1]; ORCiD logo [2];  [3]; ORCiD logo [2]
  1. University of California, Riverside
  2. ORNL
  3. University of California Riverside
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1798620
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: 25th International Conference on Pattern Recognition - Milan, , Italy - 1/10/2021 5:00:00 AM-1/15/2021 5:00:00 AM
Country of Publication:
United States
Language:
English

Citation Formats

Pasricha, Ravdeep Singh, Devineni, Pravallika, Papalexakis, Evangelos E., and Kannan, Ramakrishnan. Tensorized Feature Spaces for Feature Explosion. United States: N. p., 2021. Web.
Pasricha, Ravdeep Singh, Devineni, Pravallika, Papalexakis, Evangelos E., & Kannan, Ramakrishnan. Tensorized Feature Spaces for Feature Explosion. United States.
Pasricha, Ravdeep Singh, Devineni, Pravallika, Papalexakis, Evangelos E., and Kannan, Ramakrishnan. 2021. "Tensorized Feature Spaces for Feature Explosion". United States. https://www.osti.gov/servlets/purl/1798620.
@article{osti_1798620,
title = {Tensorized Feature Spaces for Feature Explosion},
author = {Pasricha, Ravdeep Singh and Devineni, Pravallika and Papalexakis, Evangelos E. and Kannan, Ramakrishnan},
abstractNote = {In this paper 1 1 This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-000R22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan) This research used resources of the Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC05-000R22725., we present a novel framework that uses tensor factorization to generate richer feature spaces for pixel classification in hyperspectral images. In particular, we assess the performance of different tensor rank decomposition methods as compared to the traditional kernel-based approaches for the hyperspectral image classification problem. We propose Orion, which takes as input a hyperspectral image tensor and a rank and outputs an enhanced feature space from the factor matrices of the decomposed tensor. Our method is a feature explosion technique that inherently maps low dimensional input space in $\mathbb{R}^{K}$ to high dimensional space in $\mathbb{R}^{R}$ , where $R\gg K$ , say in the order of 1000x, like a kernel. We show how the proposed method exploits the multi-linear structure of hyperspectral three dimensional tensor. We demonstrate the effectiveness of our method with experiments on three publicly available hyperspectral datasets with labeled pixels and compare their classification performance against traditional linear and non-linear supervised learning methods such as SVM with Linear, Polynomial, RBF kernels, and the Multi-Layer Perceptron model. Finally, we explore the relationship between the rank of the tensor decomposition and the classification accuracy using several hyperspectral datasets with ground truth.},
doi = {},
url = {https://www.osti.gov/biblio/1798620}, journal = {},
number = ,
volume = ,
place = {United States},
year = {2021},
month = {1}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: