Eprint first made available on ORBilu (E-prints, Working papers and Research blog)
Industrial defect detection on the edge with deep learning over scarcely labeled and extremely imbalanced data
Lorentz, Joe; Hartmann, Thomas; Moawad, Assaad et al.
n.d.
 

Files


Full Text
pre-print.pdf
Author preprint (5.71 MB)
This is a pre-print version of the article that is currently undergoing peer review
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
quality assurance; edge computation; semi-supervised learning; imbalanced data
Abstract :
[en] Abstract—Reliable automated defect detection is an integral part of modern manufacturing and improved performance can provide a competitive advantage. Despite the proven capabilities of convolutional neural networks (CNNs) for image classification, application on real world tasks remains challenging due to the high demand for labeled and well balanced data of the common supervised learning scheme. Semi-supervised learning (SSL) promises to achieve comparable accuracy while only requiring a small fraction of the training samples to be labeled. However, SSL methods struggle with data imbalance and existing benchmarks do not reflect the challenges of real world applications. In this work we present a CNN-based defect detection unit for thermal sensors. We describe how to collect data from a running process and release our dataset of 1k labeled and 293k unlabeled samples. Furthermore, we investigate the use of SSL under this challenging real world task.
Disciplines :
Computer science
Author, co-author :
Lorentz, Joe ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Hartmann, Thomas
Moawad, Assaad
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Language :
English
Title :
Industrial defect detection on the edge with deep learning over scarcely labeled and extremely imbalanced data
Publication date :
n.d.
Focus Area :
Computational Sciences
FnR Project :
FNR14297122 - Towards Edge-optimized Deep Learning For Explainable Quality Control, 2019 (01/01/2020-31/12/2023) - Joe Lorentz
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 11 April 2023

Statistics


Number of views
44 (0 by Unilu)
Number of downloads
37 (2 by Unilu)

Bibliography


Similar publications



Contact ORBilu