• Home
  • Search
  • Self-constructing graph neural networks to model long-range pixel dependencies for semantic segmentation of remote sensing images
  • Open Access IconOpen Access
  • Cite Icon17
  • https://doi.org/10.1080/01431161.2021.1936267Copy DOI Icon

Self-constructing graph neural networks to model long-range pixel dependencies for semantic segmentation of remote sensing images

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

ABSTRACT Capturing global contextual representations in remote sensing images by exploiting long-range pixel–pixel dependencies has been shown to improve segmentation performance. However, how to do this efficiently is an open question as current approaches of utilizing attention schemes, or very deep models to increase the field of view, increases complexity and memory consumption. Inspired by recent work on graph neural networks, we propose the Self-Constructing Graph (SCG) module that learns a long-range dependency graph directly from the image data and uses it to capture global contextual information efficiently to improve semantic segmentation. The SCG module provides a high degree of flexibility for constructing segmentation networks that seamlessly make use of the benefits of variants of graph neural networks (GNN) and convolutional neural networks (CNN). Our SCG-GCN model, a variant of SCG-Net built upon graph convolutional networks (GCN), performs semantic segmentation in an end-to-end manner with competitive performance on the publicly available ISPRS Potsdam and Vaihingen datasets, achieving a mean F1-scores of 92.0% and 89.8%, respectively. We conclude that the SCG-Net is an attractive architecture for semantic segmentation of remote sensing images since it achieves competitive performance with much fewer parameters and lower computational cost compared to related models based on convolutional neural networks.

Similar Papers
  • Conference Article
  • Citations1

Hybrid text classification model based on graph convolution network and neural network

  • Jun 01, 2023
  • Zhaohe Dong +2
  • Research Article
  • Citations148

Building segmentation through a gated graph convolutional neural network with deep structured feature embedding

  • Dec 02, 2019
  • Isprs Journal of Photogrammetry and Remote Sensing
  • Yilei Shi +2
  • Research Article
  • Citations39

GPF-Net: Graph-Polarized Fusion Network for Hyperspectral Image Classification

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Qixing Yu +5
  • Conference Article
  • Citations2

Graph Convolutional Networks: An Analysis of Method and Applications in Different Fields and Systems

  • Jul 01, 2020
  • Hongrui Peng
  • Research Article
  • Citations15

Multi-level graph convolutional recurrent neural network for semantic image segmentation

  • Mar 25, 2021
  • Telecommunication Systems
  • Dingchao Jiang +4
  • Research Article
  • Citations8

Intelligent recommendation system for College English courses based on graph convolutional networks

  • Apr 01, 2024
  • Heliyon
  • Chen Lilan +1
  • Research Article
  • Citations4

A Small Sample Recognition Model for Poisonous and Edible Mushrooms based on Graph Convolutional Neural Network.

  • Aug 12, 2022
  • Computational intelligence and neuroscience
  • Li Zhu +3
  • Research Article

Improved Dynamic Graph Convolutional Neural Network for Semantic Segmentation of Railway Scenes

  • Jan 01, 2025
  • Journal of Computer-Aided Design & Computer Graphics
  • Weidong Wang +5
  • Research Article

Enhanced Fault Detection in Induction Motors via Complex‐Value Spatio‐Temporal Graph Convolutional Neural Networks and High Level Target Navigation Pigeon Inspired Optimization

  • Mar 10, 2026
  • International Journal of Adaptive Control and Signal Processing
  • M S Saranya +1
  • Research Article
  • Citations2

Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency

  • May 11, 2025
  • Advanced Intelligent Systems
  • Renjie Xu +7
  • Conference Article
  • Citations1

First-Order Meta-Learning in Node Classification with Graph Convolutional Network

  • May 28, 2021
  • Jing Cao +2
  • Dissertation

Graph convolutional neural networks for 3D data analysis

  • Feb 22, 2023
  • Albert Mosella Montoro
  • PDF
  • Research Article
  • Citations34

A deep graph convolutional neural network architecture for graph classification.

  • Mar 10, 2023
  • PloS one
  • Yuchen Zhou +3
  • Research Article
  • Citations23

LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation

  • Jun 09, 2023
  • Expert Systems with Applications
  • Ruiqin Wang +2
  • Research Article
  • Citations1

Cross-subject emotion recognition in brain-computer interface based on frequency band attention graph convolutional adversarial neural networks

  • Sep 03, 2024
  • Journal of Neuroscience Methods
  • Shinan Chen +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.