W-Net: Convolutional neural network for segmenting remote sensing images by dual path semantics
PLOS ONE · 2023
DOI: 10.1371/journal.pone.0288311 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Guangjie Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Changchun Normal University, Changchun, Jilin, China. Hauptthemen laut MEDLINE: Remote Sensing Technology, Semantics. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Science and Technology Research and Development Project of Jilin Province, Joint fund of Science & Technology Department of Liaoning Province and State Key Laboratory of Robotics, China, Jilin Provincial Education Department Project.
Abstract (Originalsprache)
In the latest research progress, deep neural networks have been revolutionized by frameworks to extract image features more accurately. In this study, we focus on an attention model that can be useful in deep neural networks and propose a simple but strong feature extraction deep network architecture, W-Net. The architecture of our W-Net network has two mutually independent path structures, and it is designed with the following advantages. (1) There are two independent effective paths in our proposed network structure, and the two paths capture more contextual information from different scales in different ways. (2) The two paths acquire different feature images, and in the upsampling approach, we use bilinear interpolation thus reducing the feature map distortion phenomenon and integrating the different images processed. (3) The feature image processing is at a bottleneck, and a hierarchical attention module is constructed at the bottleneck by reclassifying after the channel attention module and the spatial attention module, resulting in more efficient and accurate processing of feature images. During the experiment, we also tested iSAID, a massively high spatial resolution remote sensing image dataset, with further experimental data comparison to demonstrate the generality of our method for remote sensor image segmentation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Computer Science and Technology, Changchun Normal University, Changchun, Jilin, China.
- FAW Mold Manufacturing Co., Ltd, Changchun, Jilin, China.
ORCID-Profile: Qi Wang
Förderung
- Key Science and Technology Research and Development Project of Jilin Province
- Joint fund of Science & Technology Department of Liaoning Province and State Key Laboratory of Robotics, China
- Jilin Provincial Education Department Project
Zitieren
APA
Liu, G., Wang, Q., Zhu, J., & Hong, H. (2023). W-Net: Convolutional neural network for segmenting remote sensing images by dual path semantics. PLOS ONE. https://doi.org/10.1371/journal.pone.0288311
Vancouver
Liu G, Wang Q, Zhu J, Hong H. W-Net: Convolutional neural network for segmenting remote sensing images by dual path semantics. PLOS ONE. 2023. doi:10.1371/journal.pone.0288311
BibTeX
@article{Liu2023,
author = {Liu, Guangjie and Wang, Qi and Zhu, Jinlong and Hong, Haotong},
title = {W-Net: Convolutional neural network for segmenting remote sensing images by dual path semantics},
journal = {PLOS ONE},
year = {2023},
doi = {10.1371/journal.pone.0288311}
}
EUVIMED