Multiscale depthwise separable convolution based network for high-resolution image segmentation

Ke Zhang, Inuwa Mamuda Bello, Yu Su, Jingyu Wang, Ibrahim Maryam

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Deep learning-based segmentation methods have demonstrated significant performance over their traditional counterparts. However, striving for better accuracy with such networks usually leads to the deterioration of the network’s computational efficiency, thereby rendering them inefficient for deployment on resource constraint devices. Establishing the required tradeoff between the accuracy of pixel prediction and computational efficiency remains challenging. In this article, a lightweight multiscale segmentation framework is proposed. We leverage the representation power of different receptive fields to attain optimal accuracy while maintaining computational efficiency by embedding the sparse network architecture with the depthwise separable convolution at the multiscale level. Experimental results from two challenging remote sensing segmentation datasets show that the proposed network can achieve substantial pixel prediction accuracy at relatively low computational overhead compared to state-of-the-art networks.

Original languageEnglish
Pages (from-to)6624-6643
Number of pages20
JournalInternational Journal of Remote Sensing
Volume43
Issue number18
DOIs
StatePublished - 2022

Keywords

  • depthwise separable convolution
  • Multiscale
  • remote sensing
  • segmentation

Fingerprint

Dive into the research topics of 'Multiscale depthwise separable convolution based network for high-resolution image segmentation'. Together they form a unique fingerprint.

Cite this