Unsupervised Domain Adaptation With Dense-Based Compaction for Hyperspectral Imagery

Thumbnail Image

Files

Unsupervised_Domain_Adaptation_With_Dense-Based_Compaction_for_Hyperspectral_Imagery.pdf (5.83 MB)

Links to Files

https://ieeexplore.ieee.org/document/9619921

Permanent Link

https://doi.org/10.1109/JSTARS.2021.3128932
 http://hdl.handle.net/11603/26285

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-5450-4891

Date

2021-11-18

Type of Work

journal articles
Text

Department

Program

Citation of Original Publication

C. Yu, C. Liu, H. Yu, M. Song and C. -I. Chang, "Unsupervised Domain Adaptation With Dense-Based Compaction for Hyperspectral Imagery," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 12287-12299, 2021, doi: 10.1109/JSTARS.2021.3128932.

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution 4.0 International (CC BY 4.0)

Subjects

Abstract

Enormously hard work of label obtaining leads to the lack of enough annotated samples in the hyperspectral imagery (HSI). The mentioned reality inferred the unsupervised classification performance barely satisfactorily. Unsupervised domain adaptation is exploited for knowledge delivery from a labeled source domain to boost the performance on an unlabeled target domain. In this article, we propose an unsupervised domain adaptation architecture with dense-based compaction (UDAD) for HSI classification (HSIC). The processes of spectral–spatial feature compaction, unsupervised domain adaptation, and classifier training are incorporated with an integrated framework to complete the HSI cross-scene classification. The core of the proposed framework is to utilize adversarial domain learning to reduce the domain discrepancy. To this end, the classifier trained in the source domain would accomplish well in the target domain for the unsupervised HSIC. Besides, to extract the discriminative spectral–spatial feature for the HSI domains, a dense-based compaction network is applied to complete the semisymmetric mapping. Our experiments illustrate that the UDAD model yields more effective classification performance than other state-of-the-art unsupervised HSIC methods.