Deep Metric Learning-Based Semi-Supervised Regression with Alternate Learning

dc.contributor.authorZell, Adina
dc.contributor.authorSumbul, Gencer
dc.contributor.authorDemir, Begum
dc.date.accessioned2023-11-15T10:08:09Z
dc.date.available2023-11-15T10:08:09Z
dc.date.issued2022-10-16
dc.description.abstractThis paper introduces a novel deep metric learning-based semi-supervised regression (DML-S2R) method for parameter estimation problems. The proposed DML-S2R method aims to mitigate the problems of insufficient amount of labeled samples without collecting any additional sample with a target value. To this end, it is made up of two main steps: i) pairwise similarity modeling with scarce labeled data; and ii) triplet-based metric learning with abundant unlabeled data. The first step aims to model pairwise sample similarities by using a small number of labeled samples. This is achieved by estimating the target value differences of labeled samples with a Siamese neural network (SNN). The second step aims to learn a triplet-based metric space (in which similar samples are close to each other and dissimilar samples are far apart from each other) when the number of labeled samples is insufficient. This is achieved by employing the SNN of the first step for triplet-based deep metric learning that exploits not only labeled samples but also unlabeled samples. For the end-to-end training of DML-S2R, we investigate an alternate learning strategy for the two steps. Due to this strategy, the encoded information in each step becomes a guidance for learning phase of the other step. The experimental results confirm the success of DML-S2R compared to the state-of-the-art semi-supervised regression methods. The code of the proposed method is publicly available at https://git.tu-berlin.de/rsim/DML-S2R.en
dc.description.sponsorshipEC/H2020/759764/EU/Accurate and Scalable Processing of Big Data in Earth Observation/BigEarth
dc.identifier.eissn2381-8549
dc.identifier.issn1522-4880
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/20635
dc.identifier.urihttps://doi.org/10.14279/depositonce-19433
dc.language.isoen
dc.publisherIEEE
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/
dc.subject.ddc000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::004 Datenverarbeitung; Informatik
dc.subject.othersemi-supervised regressionen
dc.subject.otherparameter estimationen
dc.subject.othermetric learningen
dc.subject.otherdeep learningen
dc.titleDeep Metric Learning-Based Semi-Supervised Regression with Alternate Learning
dc.typeConference Object
dc.type.versionacceptedVersion
dcterms.bibliographicCitation.doi10.1109/icip46576.2022.9897939
dcterms.bibliographicCitation.originalpublishernameIEEE
dcterms.bibliographicCitation.originalpublisherplaceNew York, NY
dcterms.bibliographicCitation.proceedingstitle2022 IEEE International Conference on Image Processing (ICIP)
dcterms.rightsHolder.note© 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.
dcterms.rightsHolder.referenceVerlagspolicy
dcterms.rightsHolder.urlhttps://web.archive.org/web/20230604081241/https://conferences.ieeeauthorcenter.ieee.org/author-ethics/guidelines-and-policies/post-publication-policies/#accepted
tub.accessrights.dnbembargoed*
tub.affiliationFak. 4 Elektrotechnik und Informatik::Inst. Technische Informatik und Mikroelektronik::FG Remote Sensing Image Analysis Group
tub.publisher.universityorinstitutionTechnische Universität Berlin

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Zell_etal_Deep_2022.pdf
Size:
296.97 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.23 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections