liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Dsfer-Net: A Deep Supervision and Feature Retrieval Network for Bitemporal Change Detection Using Modern Hopfield Networks
Linköping University, Department of Electrical Engineering, Information Coding. Linköping University, Faculty of Science & Engineering. Inst Adv Res Artificial Intelligence, Austria.ORCID iD: 0000-0002-9785-7937
Inst Adv Res Artificial Intelligence, Austria.
Helmholtz Zentrum Dresden Rossendorf, Germany; Univ Lancaster, England.
Wuhan Univ, Peoples R China.
2024 (English)In: IEEE Transactions on Geoscience and Remote Sensing, ISSN 0196-2892, E-ISSN 1558-0644, Vol. 62, article id 5631914Article in journal (Refereed) Published
Abstract [en]

Change detection, an essential application for high-resolution remote sensing (RS) images, aims to monitor and analyze changes in the land surface over time. Due to the rapid increase in the quantity of high-resolution RS data and the complexity of texture features, several quantitative deep learning-based methods have been proposed. These methods outperform traditional change detection (CD) methods by extracting deep features and combining spatial-temporal information. However, reasonable explanations for how deep features improve detection performance are still lacking. In our investigations, we found that modern Hopfield network (MHN) layers significantly enhance semantic understanding. In this article, we propose a deep supervision and feature retrieval network (Dsfer-Net) for bitemporal CD. Specifically, the highly representative deep features of bitemporal images are jointly extracted through a fully convolutional Siamese network. Based on the sequential geographical information of the bitemporal images, we designed a feature retrieval module to extract difference features and leverage discriminative information in a deeply supervised manner. In addition, we observed that the deeply supervised feature retrieval (DSFR) module provides explainable evidence of the semantic understanding of the proposed network in its deep layers. Finally, our end-to-end network establishes a novel framework by aggregating retrieved features and feature pairs from different layers. Experiments conducted on three public datasets (LEVIR-CD, WHU-CD, and CDD) confirm the superiority of the proposed Dsfer-Net over other state-of-the-art methods. Compared to the best-performing DSAMNet, Dsfer-Net demonstrates significant improvements, with F1 scores increasing by 4.7%, 5.9%, and 2.3%. Furthermore, compared to our previous FrNet, Dsfer-Net also achieves noteworthy enhancements, with F1 scores increasing by 2.0%, 1.4%, and 4.5% on three datasets. The code will be available online ( https://github.com/ShizhenChang/Dsfer-Net ).

Place, publisher, year, edition, pages
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC , 2024. Vol. 62, article id 5631914
Keywords [en]
Feature extraction; Semantics; Remote sensing; Long short term memory; Data mining; Hopfield neural networks; Deep learning; Change detection; high-resolution optical remote sensing (RS); modern Hopfield networks (MHNs); Siamese convolutional network
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:liu:diva-207480DOI: 10.1109/TGRS.2024.3424532ISI: 001272260000022OAI: oai:DiVA.org:liu-207480DiVA, id: diva2:1896515
Note

Funding Agencies|Institute of Advanced Research in Artificial Intelligence (IARAI)

Available from: 2024-09-10 Created: 2024-09-10 Last updated: 2024-12-03

Open Access in DiVA

fulltext(3003 kB)84 downloads
File information
File name FULLTEXT01.pdfFile size 3003 kBChecksum SHA-512
ebbf25deb05b2f93ef797c48ff26bdfea88c2ff555075275ab0b5c579da450e1bcca5a43740b2ad241d9d52b00c3af7002adbda6412efa0fdbed4645413edda7
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Chang, Shizhen
By organisation
Information CodingFaculty of Science & Engineering
In the same journal
IEEE Transactions on Geoscience and Remote Sensing
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 86 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 192 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf