Article:
Few-shot learning in industrial applications

Simple item page
dc.audienceResearchersen
dc.contributor.authorMolek, Vojtech
dc.contributor.authorAlijani, Zahra
dc.date.accessioned2026-02-06T11:29:30Z
dc.date.available2026-02-06T11:29:30Z
dc.date.issued2026
dc.description.abstractThis paper reports on the empirical performance of few-shot learning (FSL) for visual defect classification using confidential industrial datasets. We evaluate 16 combinations of four backbone models (Perception Encoder, DINOv2, DINOv3, ConvNeXt-v2) and four FSL classifiers (Prototypical Networks, Neighborhood Component Analysis, Relation Networks, Linear Adapter). The evaluation covers three conditions: a baseline comparison, deterministic support set augmentation, and a learnable attention preprocessor. Results demonstrate that support set augmentation is a highly effective strategy, improving performance in nearly all configurations. Furthermore, the DINOv2 and ConvNeXt-V2-T backbones emerged as top performers, achieving the most competitive and highest-accuracy results, respectively. These findings suggest that for industrial FSL applications, combining a strong, pre-trained backbone with a simple augmentation strategy is a practical approach for building data-efficient classification systems.en
dc.description.sponsorshipThe contribution has been funded from the project “Research of Excellence on Digital Technologies and Wellbeing CZ.02.01.01/00/22 008/0004583”, which is co-financed by the European Union. This article has been produced with the financial support of the European Union under the REFRESH – Research Excellence For REgion Sustainability and High-tech Industries project number CZ.10.03.01/00/22 003/0000048 via the Operational Programme Just Transition.
dc.identifier.citationMOLEK, Vojtech and ALIJANI, Zahra, 2026. Few-shot learning in industrial applications. Online. In: STUPŇANOVÁ, Andrea; DYBA, Martin and PAVLISKA, Viktor (eds.). Proceedings of The Eighteenth International Conference on Fuzzy Set Theory and Applications. Ostrava: University of Ostrava, p. 74-77. ISBN 978-80-7599-515-5. Available at: https://doi.org/10.15452/978-80-7599-515-5.2026.14.en
dc.identifier.doi10.15452/978-80-7599-515-5.2026.14
dc.identifier.urihttps://eduo.osu.cz/handle/1/237
dc.language.isoen
dc.rights.licenseCC BY 4.0
dc.subjectfuzzy systemsen
dc.subjectmathematicsen
dc.subjectinformaticsen
dc.subject.czenasfuzzy systémycz
dc.subject.czenasmatematikacz
dc.subject.czenasinformatikacz
dc.subject.konspekt519.1/.8 - Kombinatorika. Teorie grafů. Matematická statistika. Operační výzkum. Matematické modelovánícz
dc.titleFew-shot learning in industrial applicationsen
dc.typeinfo:eu-repo/semantics/conferencePaper
dcterms.eventThe Eighteenth International Conference on Fuzzy Set Theory and Applications, Liptovský Ján, January 25 – 30, 2026
dspace.entity.typeArticle
oaire.resourceTypeconference paper
oaire.versioninfo:eu-repo/semantics/publishedVersion
relation.isPublicationOfArticle6afab15b-8c40-42f9-a7ec-39737fc00100
relation.isPublicationOfArticle.latestForDiscovery6afab15b-8c40-42f9-a7ec-39737fc00100
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
14.pdf
Size:
340.38 KB
Format:
Adobe Portable Document Format
Download
Collections
články