Dense connection and depthwise separable convolution based CNN for polarimetric SAR image classification

Research output: Contribution to journalArticle

Authors

  • Ronghua Shang
  • Jianghai He
  • Jiaming Wang
  • Kaiming Xu
  • Licheng Jiao

Colleges, School and Institutes

Abstract

Convolution neural networks (CNN) have achieved great success in natural image processing where large amounts of training data are available. However, for the polarimetric synthetic aperture radar (PolSAR) image classification problem, the number of labeled training samples is typically limited. To improve the performance of CNN on limited training data, we propose a new network, the densely connected and depthwise separable convolutional neural network (DSNet). According to characteristics of PolSAR data, DSNet uses depthwise separable convolution to replace standard convolution, to independently extract features over each channel in PolSAR images. DSNet also introduces dense connections to directly connect non-adjacent layers. With the depthwise separable convolution and dense connections, DSNet can avoid extracting redundant features, reuse the hierarchical feature maps of PolSAR images and reduce the number of training parameters. Compared with normal CNN, DSNet is more lightweight and its training parameters decrease to less than 1/9. We compare DSNet against several popular algorithms on three different data sets, and show that DSNet achieves better results while using less training samples.

Details

Original languageEnglish
Article number105542
JournalKnowledge-Based Systems
Early online date23 Jan 2020
Publication statusE-pub ahead of print - 23 Jan 2020

Keywords

  • DSNet, polarimetric SAR image classification, convolutional neural networks, depthwise separable convolution, dense connection