Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-22256
Publication type: Conference paper
Type of review: Peer review (publication)
Title: A survey of un-, weakly-, and semi-supervised learning methods for noisy, missing and partial labels in industrial vision applications
Authors: Simmler, Niclas
Sager, Pascal
Andermatt, Philipp
Chavarriaga, Ricardo
Schilling, Frank-Peter
Rosenthal, Matthias
Stadelmann, Thilo
et. al: No
DOI: 10.21256/zhaw-22256
Published in: Proceedings of the 8th SDS
Conference details: 8th Swiss Conference on Data Science, Lucerne, Switzerland, 9 June 2021
Issue Date: 9-Jun-2021
Publisher / Ed. Institution: IEEE
Language: English
Subjects: Deep learning; Computer vision; Label quality
Subject (DDC): 006: Special computer methods
Abstract: When applying deep learning methods in an industrial vision application, they often fall short of the performance shown in a clean and controlled lab environment due to data quality issues. Few would consider the actual labels as a driving factor, yet inaccurate label data can impair model performance significantly. However, being able to mitigate inaccurate or incomplete labels might also be a cost-saver for real-world projects. Here, we survey state-of-the-art deep learning approaches to resolve such missing labels, noisy labels, and partially labeled data in the prospect of an industrial vision application. We systematically present un-, weakly, and semi-supervised approaches from ’A’ like anomaly detection to ’Z’ like zero-shot classification to resolve these challenges by embracing them.
Further description: ​© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: https://digitalcollection.zhaw.ch/handle/11475/22256
Fulltext version: Accepted version
License (according to publishing contract): Licence according to publishing contract
Departement: School of Engineering
Organisational Unit: Centre for Artificial Intelligence (CAI)
Institute of Applied Information Technology (InIT)
Institute of Embedded Systems (InES)
Published as part of the ZHAW project: FWA: Visual Food Waste Analysis for Sustainable Kitchens
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2021_Simmler-etal_Learning-methods-labels-industrial-vision-applications_SDS.pdfAccepted Version137.43 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.