KIT | KIT-Bibliothek | Impressum | Datenschutz

Similarity-Based Framework for Unsupervised Domain Adaptation: Peer Reviewing Policy for Pseudo-Labeling

Arweiler, Joel 1; Ates, Cihan ORCID iD icon 2; Cerquides, Jesus; Koch, Rainer 1; Bauer, Hans-Jörg 1
1 Karlsruher Institut für Technologie (KIT)
2 Institut für Thermische Strömungsmaschinen (ITS), Karlsruher Institut für Technologie (KIT)

Abstract:

The inherent dependency of deep learning models on labeled data is a well-known problem and one of the barriers that slows down the integration of such methods into different fields of applied sciences and engineering, in which experimental and numerical methods can easily generate a colossal amount of unlabeled data. This paper proposes an unsupervised domain adaptation methodology that mimics the peer review process to label new observations in a different domain from the training set. The approach evaluates the validity of a hypothesis using domain knowledge acquired from the training set through a similarity analysis, exploring the projected feature space to examine the class centroid shifts. The methodology is tested on a binary classification problem, where synthetic images of cubes and cylinders in different orientations are generated. The methodology improves the accuracy of the object classifier from 60% to around 90% in the case of a domain shift in physical feature space without human labeling.


Verlagsausgabe §
DOI: 10.5445/IR/1000164435
Veröffentlicht am 16.11.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Thermische Strömungsmaschinen (ITS)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2023
Sprache Englisch
Identifikator ISSN: 2504-4990
KITopen-ID: 1000164435
Erschienen in Machine Learning and Knowledge Extraction
Verlag MDPI
Band 5
Heft 4
Seiten 1474–1492
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Vorab online veröffentlicht am 12.10.2023
Schlagwörter unsupervised domain adaptation; pseudo-labeling; transfer learning
Nachgewiesen in Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page