Show simple item record

dc.contributor.authorSingh, Durgesh Kumar
dc.contributor.authorBoubekki, Ahcene
dc.contributor.authorJenssen, Robert
dc.contributor.authorKampffmeyer, Michael
dc.date.accessioned2024-02-16T14:13:44Z
dc.date.available2024-02-16T14:13:44Z
dc.date.issued2023-05-05
dc.description.abstractThe development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex training strategies to obtain the desired results. In this work, we instead propose a novel approach that explicitly incorporates the underlying clustering assumption in SSL through extending a recently proposed differentiable clustering module. Leveraging annotated data to guide the cluster centroids results in a simple end-to-end trainable deep SSL approach. We demonstrate that the proposed model improves the performance over the supervised-only baseline and show that our framework can be used in conjunction with other SSL methods to further boost their performance.en_US
dc.identifier.citationSingh, Boubekki, Jenssen, Kampffmeyer. Supercm: Revisiting Clustering for Semi-Supervised Learning. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. 2023en_US
dc.identifier.cristinIDFRIDAID 2168107
dc.identifier.doi10.1109/ICASSP49357.2023.10095856
dc.identifier.issn1520-6149
dc.identifier.issn2379-190X
dc.identifier.urihttps://hdl.handle.net/10037/32960
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.journalProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
dc.relation.projectIDSigma2: NN8106Ken_US
dc.relation.projectIDNorges forskningsråd: 309439en_US
dc.relation.projectIDNorges forskningsråd: 315029en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2023 The Author(s)en_US
dc.titleSupercm: Revisiting Clustering for Semi-Supervised Learningen_US
dc.type.versionacceptedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record