Show simple item record

dc.contributor.authorYe, Minchao
dc.contributor.authorQian, Yuntao
dc.contributor.authorZhou, Jun
dc.contributor.authorTang, Yuan Yan
dc.date.accessioned2017-08-04T12:30:52Z
dc.date.available2017-08-04T12:30:52Z
dc.date.issued2017
dc.identifier.issn0196-2892
dc.identifier.doi10.1109/TGRS.2016.2627042
dc.identifier.urihttp://hdl.handle.net/10072/340635
dc.description.abstractA big challenge of hyperspectral image (HSI) classification is the small size of labeled pixels for training classifier. In real remote sensing applications, we always face the situation that an HSI scene is not labeled at all, or is with very limited number of labeled pixels, but we have sufficient labeled pixels in another HSI scene with the similar land cover classes. In this paper, we try to classify an HSI scene containing no labeled sample or only a few labeled samples with the help of a similar HSI scene having a relative large size of labeled samples. The former scene is defined as the target scene, while the latter one is the source scene. We name this classification problem as cross-scene classification. The main challenge of cross-scene classification is spectral shift, i.e., even for the same class in different scenes, their spectral distributions maybe have significant deviation. As all or most training samples are drawn from the source scene, while the prediction is performed in the target scene, the difference in spectral distribution would greatly deteriorate the classification performance. To solve this problem, we propose a dictionary learning-based feature-level domain adaptation technique, which aligns the spectral distributions between source and target scenes by projecting their spectral features into a shared low-dimensional embedding space by multitask dictionary learning. The basis atoms in the learned dictionary represent the common spectral components, which span a cross-scene feature space to minimize the effect of spectral shift. After the HSIs of two scenes are transformed into the shared space, any traditional HSI classification approach can be used. In this paper, sparse logistic regression (SRL) is selected as the classifier. Especially, if there are a few labeled pixels in the target domain, multitask SRL is used to further promote the classification performance. The experimental results on synthetic and real HSIs show the advantages of the proposed method for cross-scene classification.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherInstitute of Electircal and Electronics Engineers
dc.relation.ispartofpagefrom1544
dc.relation.ispartofpageto1562
dc.relation.ispartofissue3
dc.relation.ispartofjournalIEEE Transactions on Geoscience and Remote Sensing
dc.relation.ispartofvolume55
dc.subject.fieldofresearchElectrical and Electronic Engineering not elsewhere classified
dc.subject.fieldofresearchGeophysics
dc.subject.fieldofresearchElectrical and Electronic Engineering
dc.subject.fieldofresearchGeomatic Engineering
dc.subject.fieldofresearchcode090699
dc.subject.fieldofresearchcode0404
dc.subject.fieldofresearchcode0906
dc.subject.fieldofresearchcode0909
dc.titleDictionary Learning-Based Feature-Level Domain Adaptation for Cross-Scene Hyperspectral Image Classification
dc.typeJournal article
dc.type.descriptionC1 - Articles
dc.type.codeC - Journal Articles
dc.description.versionPost-print
gro.rights.copyright© 2017 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.
gro.hasfulltextFull Text
gro.griffith.authorZhou, Jun


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record