Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/29479
Title: | Lightweight Structure-Aware Transformer Network for Remote Sensing Image Change Detection |
Authors: | Lei, T Xu, Y Ning, H Lv, Z Min, C Jin, Y Nandi, AK |
Keywords: | change detection (CD);deep learning;remote sensing (RS) image;transformer |
Issue Date: | 16-Oct-2024 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Citation: | Lei, T. et al. (2024) 'Lightweight Structure-Aware Transformer Network for Remote Sensing Image Change Detection'. IEEE Geoscience and Remote Sensing Letters, 21, 6000305, pp. 1 - 5. doi: 10.1109/LGRS.2023.3323534. |
Abstract: | Popular Transformer networks have been successfully applied to remote sensing (RS) image change detection (CD) identifications and achieved better results than most convolutional neural networks (CNNs), but they still suffer from two main problems. First, the computational complexity of the Transformer grows quadratically with the increase of image spatial resolution, which is unfavorable to RS images. Second, these popular Transformer networks tend to ignore the importance of fine-grained features, which results in poor edge integrity and internal tightness for largely changed objects and leads to the loss of small changed objects. To address the above issues, this letter proposes a lightweight structure-aware Transformer (LSAT) network for RS image CD. The proposed LSAT has two advantages. First, a cross-dimension interactive self-attention (CISA) module with linear complexity is designed to replace the vanilla self-attention (SA) in the visual Transformer, which effectively reduces the computational complexity while improving the feature representation ability of the proposed LSAT. Second, a structure-aware enhancement module (SAEM) is designed to enhance difference features and edge detail information, which can achieve double enhancement by difference refinement and detail aggregation to obtain fine-grained features of bi-temporal RS images. Experimental results show that the proposed LSAT achieves significant improvement in detection accuracy and offers a better tradeoff between accuracy and computational costs than most state-of-the-art (SOTA) CD methods for RS images. |
Description: | Supplemental Items: The supplementary materials include experiments on the DSIFN-CD dataset and ablation experiments on the CDD dataset to validate our LSAT method. Furthermore, we also analyze the effect of pre-training on the performance. DOI:10.1109/LGRS.2023.3323534/mm1 . |
URI: | https://bura.brunel.ac.uk/handle/2438/29479 |
DOI: | https://doi.org/10.1109/LGRS.2023.3323534 |
ISSN: | 1545-598X |
Other Identifiers: | ORCiD: Tao Lei https://orcid.org/0000-0002-2104-9298 ORCiD: Yetong Xu https://orcid.org/0009-0008-9290-2023 ORCiD: Hailong Ning https://orcid.org/0000-0001-8375-1181 ORCiD: Zhiyong Lv https://orcid.org/0000-0003-2595-4794 ORCiD: Yaochu Jin https://orcid.org/0000-0003-1100-0631 ORCiD: Asoke K. Nandi https://orcid.org/0000-0001-6248-2875 6000305 |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Preprint.pdf | Copyright © 2023 The Authors. This is a preprint made available under the arXiv.org - Non-exclusive license to distribute, see: https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html. This arXiv preprint has been prepared for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. It has not been certified by peer review. Citation information: DOI10.1109/LGRS.2023.3323534, IEEE Geoscience and Remote Sensing Letters. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/ | 1.84 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.