HDRANet: Hybrid dilated residual attention network for SAR image despeckling

Jingyu Li, Ying Li*, Yayuan Xiao, Yunpeng Bai

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

27 Citations (SciVal)
47 Downloads (Pure)

Abstract

In order to remove speckle noise from original synthetic aperture radar (SAR) images effectively and efficiently, this paper proposes a hybrid dilated residual attention network (HDRANet) with residual learning for SAR despeckling. Firstly, HDRANet employs the hybrid dilated convolution (HDC) in lightweight network architecture to enlarge the receptive field and aggregate global information. Then, a simple yet effective attention module, convolutional block attention module (CBAM), is integrated into the proposed model to constitute a residual HDC attention block through skip connection, which further enhances representation power and performance of the model. Extensive experimental results on the synthetic and real SAR images demonstrate the superior performance of HDRANet over the state-of-the-art methods in terms of quantitative metrics and visual quality.

Original languageEnglish
Article number2921
Number of pages20
JournalRemote Sensing
Volume11
Issue number24
DOIs
Publication statusPublished - 06 Dec 2019
Externally publishedYes

Keywords

  • Attention mechanism
  • Convolution neural network
  • Hybrid dilated convolution
  • SAR image
  • Speckle

Fingerprint

Dive into the research topics of 'HDRANet: Hybrid dilated residual attention network for SAR image despeckling'. Together they form a unique fingerprint.

Cite this