• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

An Industrial Application of Semi-supervised techniques for automatic surface inspection of stainless steel. : Are pseudo-labeling and consistency regularization effective in a real industrial context?

Zoffoli, Mattia January 2022 (has links)
Recent developments in the field of Semi-Supervised Learning are working to avoid the bottleneck of data labeling. This can be achieved by leveraging unlabeled data to limit the amount of labeled data needed for training deep learning models. Semi-supervised learning algorithms are showing promising results; however, research has been focusing on algorithm development, without proceeding to test their effectiveness in real-world applications. This research project has adapted and tested some semi-supervised learning algorithms on a dataset extracted from the manufacturing en-vironment, in the context of the surface analysis of stainless steel, in collaboration with Outokumpu Stainless Oy. In particular, a simple algorithm combining Pseudo-Labeling and Consistency Regularization has been developed, inspired by the state-of-the-art algorithm Fix match. The results show some potential, because the usage of Semi-Supervised Learning techniques has significantly reduced overfitting on the training set, while maintaining a good accuracy on the test set. However, some doubts are raised regarding the application of these techniques in a real environment, due to the imperfect nature of real datasets and the high algorithm development cost due to the increased complexity introduced with these methods. / Den senaste utvecklingen inom området Semi-Supervised Learning arbetarför att undvika flaskhalsen med datamärkning. Detta kan uppnås genom att utnyttja omärkta data för att begränsa mängden märkt data som behövs för att träna modeller för djupinlärning. Semi-övervakade inlärningsalgoritmer visarlovande resultat; forskning har dock fokuserat på algoritmutveckling, utan att testa deras effektivitet i verkliga tillämpningar. Detta forskningsprojekt har anpassat och testat några semi-övervakade in-lärningsalgoritmer på en datauppsättning extraherad från tillverkningsmiljön, i samband med ytanalys av rostfritt stål, i samarbete med Outokumpu Stainless Oy. I synnerhet har en enkel algoritm som kombinerar Pseudo-Labeling och Consistency Regularization utvecklats, inspirerad av den toppmoderna algoritmen Fixmatch .Resultaten visar en viss potential, eftersom användningen av Semi-Supervised Learning-tekniker avsevärt har minskat överanpassningen av träningssetet, samtidigt som en god noggrannhet på testsetet bibehålls. Vissa tvivel reses dock angående tillämpningen av dessa tekniker i en verklig miljö, på grund av den ofullkomliga karaktären hos riktiga datauppsättningar och den höga algoritmutvecklingskostnaden på grund av den ökade komplexiteten som introduceras med dessa metoder.

Page generated in 0.1035 seconds