KIT | KIT-Bibliothek | Impressum | Datenschutz

Siamese Basis Function Networks for Data-Efficient Defect Classification in Technical Domains

Schlagenhauf, Tobias 1; Yildirim, Faruk; Brückner, Benedikt
1 Institut für Produktionstechnik (WBK), Karlsruher Institut für Technologie (KIT)


Training deep learning models in technical domains is often accompanied by the challenge that although the task is clear, insufficient data for training is available. In this work, we propose a novel approach based on the combination of Siamese networks and radial basis function networks to perform data-efficient classification without pretraining by measuring the distance between images in semantic space in a data-efficient manner. We develop the models using three technical datasets, the NEU dataset, the BSD dataset, and the TEX dataset. In addition to the technical domain, we show the general applicability to classical datasets (cifar10 and MNIST) as well. The approach is tested against state-of-the-art models (Resnet50 and Resnet101) by stepwise reduction of the number of samples available for training. The authors show that the proposed approach outperforms the state-of-the-art models in the low data regime.

Volltext §
DOI: 10.5445/IR/1000158045
Veröffentlicht am 20.04.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Produktionstechnik (WBK)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2020
Sprache Englisch
Identifikator KITopen-ID: 1000158045
Umfang 12 S.
Vorab online veröffentlicht am 02.12.2020
Schlagwörter Condition Monitoring, Deep Learning, Machine Learning, Machine Vision, Object Detection, One-shot Learning, Predictive Maintenance, Siamese Networks
Nachgewiesen in arXiv
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page