ABCNet: attentive bilateral contextual network for efficient semantic segmentation of fine-resolution remotely sensed imagery

Li, Rui; Zheng, Shunyi; Zhang, Ce ORCID: https://orcid.org/0000-0001-5100-3584; Duan, Chenxi; Wang, Libo; Atkinson, Peter M.. 2021 ABCNet: attentive bilateral contextual network for efficient semantic segmentation of fine-resolution remotely sensed imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 181. 84-98. 10.1016/j.isprsjprs.2021.09.005

Before downloading, please read NORA policies.

Preview

Text N531170JA.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (11MB) | Preview

Abstract/Summary

Semantic segmentation of remotely sensed imagery plays a critical role in many real-world applications, such as environmental change monitoring, precision agriculture, environmental protection, and economic assessment. Following rapid developments in sensor technologies, vast numbers of fine-resolution satellite and airborne remote sensing images are now available, for which semantic segmentation is potentially a valuable method. However, because of the rich complexity and heterogeneity of information provided with an ever-increasing spatial resolution, state-of-the-art deep learning algorithms commonly adopt complex network structures for segmentation, which often result in significant computational demand. Particularly, the frequently-used fully convolutional network (FCN) relies heavily on fine-grained spatial detail (fine spatial resolution) and contextual information (large receptive fields), both imposing high computational costs. This impedes the practical utility of FCN for real-world applications, especially those requiring real-time data processing. In this paper, we propose a novel Attentive Bilateral Contextual Network (ABCNet), a lightweight convolutional neural network (CNN) with a spatial path and a contextual path. Extensive experiments, including a comprehensive ablation study, demonstrate that ABCNet has strong discrimination capability with competitive accuracy compared with state-of-the-art benchmark methods while achieving significantly increased computational efficiency. Specifically, the proposed ABCNet achieves a 91.3% overall accuracy (OA) on the Potsdam test dataset and outperforms all lightweight benchmark methods significantly. The code is freely available at https://github.com/lironui/ABCNet.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	10.1016/j.isprsjprs.2021.09.005
UKCEH and CEH Sections/Science Areas:	Soils and Land Use (Science Area 2017-)
ISSN:	0924-2716
Additional Information. Not used in RCUK Gateway to Research.:	Open Access paper - full text available via Official URL link.
Additional Keywords:	semantic segmentation, attention mechanism, bilateral architecture, convolutional neural network, deep learning
NORA Subject Terms:	Electronics, Engineering and Technology
Date made live:	04 Oct 2021 16:04 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/531170

Actions (login required)

View Item

Document Downloads

More statistics for this item...