Skip to main content

Research Repository

Advanced Search

An unsupervised domain adaptation method towards multi-level features and decision boundaries for cross-scene hyperspectral image classification.

Zhao, Chunhui; Qin, Boao; Feng, Shou; Zhu, Wenxiang; Zhang, Lifu; Ren, Jinchang

Authors

Chunhui Zhao

Boao Qin

Shou Feng

Wenxiang Zhu

Lifu Zhang



Abstract

Despite success in the same-scene hyperspectral image classification (HSIC), for the cross-scene classification, samples between source and target scenes are not drawn from the independent and identical distribution, resulting in significant performance degradation. To tackle this issue, a novel unsupervised domain adaptation (UDA) framework toward multilevel features and decision boundaries (ToMF-B) is proposed for the cross-scene HSIC, which can align task-related features and learn task-specific decision boundaries in parallel. Based on the maximum classifier discrepancy, a two-stage alignment scheme is proposed to bridge the interdomain gap and generate discriminative decision boundaries. In addition, to fully learn task-related and domain-confusing features, a convolutional neural network (CNN) and Transformer-based multilevel features extractor (generator) is developed to enrich the feature representation of two domains. Furthermore, to alleviate the harm even the negative transfer to UDA caused by task-irrelevant features, a task-oriented feature decomposition method is leveraged to enhance the task-related features while suppressing task-irrelevant features, and enabling the aligned domain-invariant features can be contributed to the classification task explicitly. Extensive experiments on three cross-scene HSI benchmarks have validated the effectiveness of the proposed framework.

Citation

ZHAO, C., QIN, B., FENG, S., ZHU, W., ZHANG, L. and REN, J. 2022. An unsupervised domain adaptation method towards multi-level features and decision boundaries for cross-scene hyperspectral image classification. IEEE transactions on geoscience and remote sensing [online], 60, article 5546216. Available from: https://doi.org/10.1109/TGRS.2022.3230378

Journal Article Type Article
Acceptance Date Dec 14, 2022
Online Publication Date Dec 16, 2022
Publication Date Dec 31, 2022
Deposit Date Jan 12, 2023
Publicly Available Date Mar 28, 2024
Journal IEEE transactions on geoscience and remote sensing
Print ISSN 0196-2892
Electronic ISSN 1558-0644
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Peer Reviewed Peer Reviewed
Volume 60
Article Number 5546216
DOI https://doi.org/10.1109/TGRS.2022.3230378
Keywords Cross-scene classification; Hyperspectral image (HSI); Task irrelevant; Task specific; Unsupervised domain adaptation (UDA)
Public URL https://rgu-repository.worktribe.com/output/1843977

Files

ZHAO 2022 An unsupervised domain adaptation (AAM) (6.1 Mb)
PDF

Copyright Statement
© 2022 IEEE. 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.





You might also like



Downloadable Citations