Home > Research > Publications & Outputs > SSA-SiamNet

Electronic data

  • Final Version

    Rights statement: ©2021 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, 3.15 MB, PDF document

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

Links

Text available via DOI:

View graph of relations

SSA-SiamNet: Spectral-Spatial-Wise Attention-Based Siamese Network for Hyperspectral Image Change Detection

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published
Article number5510018
<mark>Journal publication date</mark>31/01/2022
<mark>Journal</mark>IEEE Transactions on Geoscience and Remote Sensing
Volume60
Number of pages18
Publication StatusPublished
Early online date26/07/21
<mark>Original language</mark>English

Abstract

Deep learning methods, especially convolutional neural network (CNN)-based methods, have shown promising performance for hyperspectral image (HSI) change detection (CD). It is acknowledged widely that different spectral channels and spatial locations in input image patches may contribute differently to CD. However, they are treated equally in existing CNN-based approaches. To increase the accuracy of HSI CD, we propose an end-to-end Siamese CNN (SiamNet) with a spectral-spatial-wise attention (SSA-SiamNet) mechanism. The proposed SSA-SiamNet method can emphasize informative channels and locations and suppress less informative ones to refine the spectral-spatial features adaptively. Moreover, in the network training phase, the weighted contrastive loss function is used for more reliable separation of changed and unchanged pixels and to accelerate the convergence of the network. SSA-SiamNet was validated using four groups of bitemporal HSIs. The accuracy of CD using the SSA-SiamNet was found to be consistently greater than for ten benchmark methods.

Bibliographic note

©2021 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.