Superpixel-Based Attention Graph Neural Network for Semantic Segmentation in Aerial Images

Qi Diao, Yaping Dai, Ce Zhang, Yan Wu, Xiaoxue Feng, Feng Pan*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

18 Citations (Scopus)

Abstract

Semantic segmentation is one of the significant tasks in understanding aerial images with high spatial resolution. Recently, Graph Neural Network (GNN) and attention mechanism have achieved excellent performance in semantic segmentation tasks in general images and been applied to aerial images. In this paper, we propose a novel Superpixel-based Attention Graph Neural Network (SAGNN) for semantic segmentation of high spatial resolution aerial images. A K-Nearest Neighbor (KNN) graph is constructed from our network for each image, where each node corresponds to a superpixel in the image and is associated with a hidden representation vector. On this basis, the initialization of the hidden representation vector is the appearance feature extracted by a unary Convolutional Neural Network (CNN) from the image. Moreover, relying on the attention mechanism and recursive functions, each node can update its hidden representation according to the current state and the incoming information from its neighbors. The final representation of each node is used to predict the semantic class of each superpixel. The attention mechanism enables graph nodes to differentially aggregate neighbor information, which can extract higher-quality features. Furthermore, the superpixels not only save computational resources, but also maintain object boundary to achieve more accurate predictions. The accuracy of our model on the Potsdam and Vaihingen public datasets exceeds all benchmark approaches, reaching 90.23% and 89.32%, respectively.

Original languageEnglish
Article number305
JournalRemote Sensing
Volume14
Issue number2
DOIs
Publication statusPublished - 1 Jan 2022

Keywords

  • Aerial images
  • Attention mechanism
  • Graph neural networks
  • Semantic segmentation
  • Superpixel

Fingerprint

Dive into the research topics of 'Superpixel-Based Attention Graph Neural Network for Semantic Segmentation in Aerial Images'. Together they form a unique fingerprint.

Cite this