Class-Guided Swin Transformer for Semantic Segmentation of Remote Sensing Imagery | IEEE Journals & Magazine | IEEE Xplore

Class-Guided Swin Transformer for Semantic Segmentation of Remote Sensing Imagery


Abstract:

Semantic segmentation of remote sensing images plays a crucial role in a wide variety of practical applications, including land cover mapping, environmental protection, a...Show More

Abstract:

Semantic segmentation of remote sensing images plays a crucial role in a wide variety of practical applications, including land cover mapping, environmental protection, and economic assessment. In the last decade, convolutional neural network (CNN) is the mainstream deep learning-based method of semantic segmentation. Compared with conventional methods, CNN-based methods learn semantic features automatically, thereby achieving strong representation capability. However, the local receptive field of the convolution operation limits CNN-based methods from capturing long-range dependencies. In contrast, Vision Transformer (ViT) demonstrates its great potential in modeling long-range dependencies and obtains superior results in semantic segmentation. Inspired by this, in this letter, we propose a class-guided Swin Transformer (CG-Swin) for semantic segmentation of remote sensing images. Specifically, we adopt a Transformer-based encoder–decoder structure, which introduces the Swin Transformer backbone as the encoder and designs a class-guided Transformer block to construct the decoder. The experimental results on ISPRS Vaihingen and Potsdam datasets demonstrate the significant breakthrough of the proposed method over ten benchmarks, outperforming both advanced CNN-based and recent Transformer-based approaches.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 19)
Article Sequence Number: 6517505
Date of Publication: 17 October 2022

ISSN Information:

Funding Agency:

School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
Lands and Resource Department of Guangdong Province, Key Laboratory of Natural Resources Monitoring in Tropical and Subtropical Area of South China, Ministry of Natural Resources, Surveying and Mapping Institute, Guangzhou, China
Guangdong Science and Technology Collaborative Innovation Center for Natural Resources, Guangzhou, China
Intelligent Control and Smart Energy (ICSE) Research Group, School of Engineering, University of Warwick, Coventry, U.K.
Lancaster Environment Centre, Lancaster University, Lancaster, U.K.
U.K. Centre for Ecology & Hydrology, Lancaster, U.K.

School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
Lands and Resource Department of Guangdong Province, Key Laboratory of Natural Resources Monitoring in Tropical and Subtropical Area of South China, Ministry of Natural Resources, Surveying and Mapping Institute, Guangzhou, China
Guangdong Science and Technology Collaborative Innovation Center for Natural Resources, Guangzhou, China
Intelligent Control and Smart Energy (ICSE) Research Group, School of Engineering, University of Warwick, Coventry, U.K.
Lancaster Environment Centre, Lancaster University, Lancaster, U.K.
U.K. Centre for Ecology & Hydrology, Lancaster, U.K.

Contact IEEE to Subscribe

References

References is not available for this document.