Semisupervised Edge-Aware Road Extraction via Cross Teaching Between CNN and Transformer

Semisupervised semantic segmentation of remote sensing images has been proven to be an effective approach to reduce manual annotation costs and leverage available unlabeled data to improve segmentation performance. However, some existing methods that focus on self-training and consistent regularizat...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing 2023, Vol.16, p.8353-8362
Main Authors: Yang, Zi-Xiong, You, Zhi-Hui, Chen, Si-Bao, Tang, Jin, Luo, Bin
Format: Article
Language:English
Subjects:
Artificial neural networks
Cross teaching (CT)
Data models
edge-aware
Image edge detection
Image processing
Image segmentation
Neural networks
Regularization
Remote sensing
road extraction
Roads
Semantic segmentation
semisupervised learning
Task analysis
Training
transformer
Transformers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Semisupervised semantic segmentation of remote sensing images has been proven to be an effective approach to reduce manual annotation costs and leverage available unlabeled data to improve segmentation performance. However, some existing methods that focus on self-training and consistent regularization fail to consider large-scale characteristics of remote sensing images and the importance of incorporating road edge information. In this article, we propose a novel semisupervised edge-aware network (SSEANet) for remote sensing image semantic segmentation by jointly training convolutional neural network and transformer. SSEANet focuses on the consistency loss of multiscale features and uses an attention mechanism to fuse road edge information. Extensive experiments on DeepGlobe, Massachusetts, and AerialKITTI-Bavaria datasets show that the proposed method outperforms state-of-the-art, demonstrating its effectiveness.
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2023.3310612