Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning

Haokui Zhang, Ying Li, Yenan Jiang, Peng Wang, Qiang Shen, Chunhua Shen

Research output: Contribution to journalArticlepeer-review

172 Citations (Scopus)
711 Downloads (Pure)

Abstract

Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limited available training samples and massive model parameters, DL methods may suffer from overfitting. In this paper, we propose an end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as 3-D-LWNet) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy, in which we pretrain a 3-D model in the source HSI data sets containing a greater number of labeled samples and then transfer it to the target HSI data sets and 2) cross-modal strategy, in which we pretrain a 3-D model in the 2-D RGB image data sets containing a large number of samples and then transfer it to the target HSI data sets. In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets. Experiments on three public HSI data sets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods.

Original languageEnglish
Article number8685710
Pages (from-to)5813-5828
Number of pages16
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume57
Issue number8
Early online date11 Apr 2019
DOIs
Publication statusPublished - 31 Aug 2019

Keywords

  • hyperspectral classification
  • deep learning
  • 3D lightweight convolutional network
  • transfer learning
  • 3-D lightweight convolutional network (3-D-LWNet)
  • deep learning (DL)

Fingerprint

Dive into the research topics of 'Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning'. Together they form a unique fingerprint.

Cite this