DLPNet: A deep manifold network for feature extraction of hyperspectral imagery.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date: May 22, 2020

Abstract

Deep learning has received increasing attention in recent years and it has been successfully applied for feature extraction (FE) of hyperspectral images. However, most deep learning methods fail to explore the manifold structure in hyperspectral image (HSI). To tackle this issue, a novel graph-based deep learning model, termed deep locality preserving neural network (DLPNet), was proposed in this paper. Traditional deep learning methods use random initialization to initialize network parameters. Different from that, DLPNet initializes each layer of the network by exploring the manifold structure in hyperspectral data. In the stage of network optimization, it designed a deep-manifold learning joint loss function to exploit graph embedding process while measuring the difference between the predictive value and the actual value, then the proposed model can take into account the extraction of deep features and explore the manifold structure of data simultaneously. Experimental results on real-world HSI datasets indicate that the proposed DLPNet performs significantly better than some state-of-the-art methods.

Authors

  • Zhengying Li
    Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, China. Electronic address: zhengying_li@cqu.edu.cn.
  • Hong Huang
    Department of Ecology and Evolution, University of Lausanne, 1015 Lausanne, Switzerland, SIB Swiss Institute of Bioinformatics, 1015 Lausanne, Switzerland, Department of Microbiology and Immunology and Institute for Genome Sciences, University of Maryland School of Medicine, Baltimore MD, USA, SIB Swiss Institute of Bioinformatics, 1 Rue Michel Servet, 1211 Geneva, Switzerland, Department of Medicine and Institute for Genome Sciences, University of Maryland School of Medicine, Baltimore MD, USA, Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, CA 94158, USA, School of Information, University of South Florida, Tampa, FL, 33647, USA, Genomics Division, Lawrence Berkeley National Lab, 1 Cyclotron Rd., Berkeley, 94720 CA USA, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK, Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, Geneva, Switzerland, ETH Zurich, Department of Computer Science, Universitätstr. 19, 8092 Zürich, Switzerland, SIB Swiss Institute of Bioinformatics, Universitätstr. 6, 8092 Zürich, Switzerland and University College London, Gower St, London WC1E 6BT, UK.
  • Yule Duan
    Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, China. Electronic address: duanyule@cqu.edu.cn.
  • Guangyao Shi
    Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, China. Electronic address: shiguangyao@cqu.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals