Show simple item record

dc.contributor.authorXiong, F
dc.contributor.authorZhou, J
dc.contributor.authorYe, M
dc.contributor.authorLu, J
dc.contributor.authorQian, Y
dc.date.accessioned2021-10-17T22:43:06Z
dc.date.available2021-10-17T22:43:06Z
dc.date.issued2021
dc.identifier.isbn978-1-7281-7605-5en_US
dc.identifier.issn1520-6149en_US
dc.identifier.doi10.1109/ICASSP39728.2021.9414084en_US
dc.identifier.urihttp://hdl.handle.net/10072/409140
dc.description.abstractHyperspectral unmixing is an important tool to learn the material constitution and distribution of a scene. Model-based unmixing methods depend on well-designed iterative optimization algorithms, which is usually time consuming. Learning-based methods perform unmixing in a data-driven manner but heavily rely on the quality and quantity of the training samples due to the lack of physical interpretability. In this paper, we combine the advantages of both model-based and learning-based methods and propose a nonnegative matrix factorization (NMF) inspired sparse autoencoder (NMF-SAE) for hyperspectral unmixing. NMF-SAE consists of an encoder and a decoder, both of which are constructed by unrolling the iterative optimization rules of L1 sparsity-constrained NMF for the linear spectral mixture model. All parameters in our method are obtained by end-to-end training in a data-driven manner. Our network is not only physically interpretable and flexible but also has higher learning capacity with fewer parameters. Experimental results on both synthetic and real-world data demonstrate that our method is capable of producing desirable unmixing results when compared against several alternative approaches.en_US
dc.description.peerreviewedYesen_US
dc.languageEnglishen_US
dc.publisherIEEEen_US
dc.publisher.placePiscataway, NJ, United Statesen_US
dc.relation.ispartofconferencenameICASSP 2021 - 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)en_US
dc.relation.ispartofconferencetitleICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedingsen_US
dc.relation.ispartofdatefrom2021-06-06
dc.relation.ispartofdateto2021-06-11
dc.relation.ispartoflocationVirtual - Toronto, Canadaen_US
dc.relation.ispartofpagefrom1865en_US
dc.relation.ispartofpageto1869en_US
dc.subject.fieldofresearchNanotechnologyen_US
dc.subject.fieldofresearchcode4018en_US
dc.titleNMF-SAE: An interpretable sparse autoencoder for hyperspectral unmixingen_US
dc.typeConference outputen_US
dc.type.descriptionE1 - Conferencesen_US
dcterms.bibliographicCitationXiong, F; Zhou, J; Ye, M; Lu, J; Qian, Y, NMF-SAE: An interpretable sparse autoencoder for hyperspectral unmixing, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2021, pp. 1865-1869en_US
dc.date.updated2021-10-15T05:13:22Z
dc.description.versionAccepted Manuscript (AM)en_US
gro.rights.copyright© 2021 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.en_US
gro.hasfulltextFull Text
gro.griffith.authorZhou, Jun


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record