Home > Research > Publications & Outputs > Class-guided Swin Transformer for Semantic Segm...

Electronic data

  • GRSL-01132-2022

    Rights statement: ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 2.91 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

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

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published
  • Xiaoliang Meng
  • Yuechi Yang
  • Libo Wang
  • Teng Wang
  • Rui Li
  • Ce Zhang
Close
Article number6517505
<mark>Journal publication date</mark>17/10/2022
<mark>Journal</mark>IEEE Geoscience and Remote Sensing Letters
Issue number10
Volume19
Number of pages5
Publication StatusPublished
<mark>Original language</mark>English

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.

Bibliographic note

©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.