Deep Metric and Hash-Code Learning for Content-Based Retrieval of Remote Sensing Images

dc.contributor.authorRoy, Subhankar
dc.contributor.authorSangineto, Enver
dc.contributor.authorDemir, Begüm
dc.contributor.authorSebe, Nicu
dc.date.accessioned2019-11-26T11:32:40Z
dc.date.available2019-11-26T11:32:40Z
dc.date.issued2018-11-05
dc.description© 2018 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
dc.description.abstractThe growing volume of Remote Sensing (RS) image archives demands for feature learning techniques and hashing functions which can: (1) accurately represent the semantics in the RS images; and (2) have quasi real-time performance during retrieval. This paper aims to address both challenges at the same time, by learning a semantic-based metric space for content based RS image retrieval while simultaneously producing binary hash codes for an efficient archive search. This double goal is achieved by training a deep network using a combination of different loss functions which, on the one hand, aim at clustering semantically similar samples (i.e., images), and, on the other hand, encourage the network to produce final activation values (i.e., descriptors) that can be easily binarized. Moreover, since RS annotated training images are too few to train a deep network from scratch, we propose to split the image representation problem in two different phases. In the first we use a general-purpose, pre-trained network to produce an intermediate representation, and in the second we train our hashing network using a relatively small set of training images. Experiments on two aerial benchmark archives show that the proposed method outperforms previous state-of-the-art hashing approaches by up to 5.4% using the same number of hash bits per image.en
dc.description.sponsorshipEC/H2020/759764/EU/Accurate and Scalable Processing of Big Data in Earth Observation/BigEarthen
dc.identifier.eissn2153-7003
dc.identifier.isbn978-1-5386-7150-4
dc.identifier.isbn978-1-5386-7151-1
dc.identifier.issn2153-6996
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/10402
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-9352
dc.language.isoenen
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.ddc006 Spezielle Computerverfahrende
dc.subject.otherdeep hashingen
dc.subject.othermetric learningen
dc.subject.othercontent based image retrievalen
dc.subject.otherremote sensingen
dc.titleDeep Metric and Hash-Code Learning for Content-Based Retrieval of Remote Sensing Imagesen
dc.typeConference Objecten
dc.type.versionacceptedVersionen
dcterms.bibliographicCitation.doi10.1109/IGARSS.2018.8518381en
dcterms.bibliographicCitation.originalpublishernameInstitute of Electrical and Electronics Engineers (IEEE)en
dcterms.bibliographicCitation.originalpublisherplaceNew York, NYen
dcterms.bibliographicCitation.pageend4542en
dcterms.bibliographicCitation.pagestart4539en
dcterms.bibliographicCitation.proceedingstitleIGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposiumen
tub.accessrights.dnbfreeen
tub.affiliationFak. 4 Elektrotechnik und Informatik::Inst. Technische Informatik und Mikroelektronik::FG Remote Sensing Image Analysis Groupde
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Remote Sensing Image Analysis Groupde
tub.affiliation.instituteInst. Technische Informatik und Mikroelektronikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen

Files

Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
roy_etal_2018.pdf
Size:
1017.29 KB
Format:
Adobe Portable Document Format
Description:
Accepted manuscript
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
5.75 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections