Show simple item record

dc.contributor.author
Ntavelis, Evangelos
dc.contributor.author
Kastanis, Iason
dc.contributor.author
Van Gool, Luc
dc.contributor.author
Timofte, Radu
dc.date.accessioned
2020-11-12T14:49:43Z
dc.date.available
2020-11-09T04:08:59Z
dc.date.available
2020-11-12T14:49:43Z
dc.date.issued
2020
dc.identifier.isbn
978-1-7281-7177-7
en_US
dc.identifier.isbn
978-1-7281-7178-4
en_US
dc.identifier.other
10.1109/SDS49233.2020.00011
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/450202
dc.description.abstract
The evolution of generative adversarial networks has permitted the generation of realistic fake images which, in some cases, are indistinguishable from the real ones. Many recent works in image generation focus on learning internal image statistics via training only on a single natural image. While natural images exhibit a variability in their attributes, industrial images are often acquired in a controlled environment following a specific structure. In this work we utilize the cutting-edge results of single image generation on the structured case of industrial images. Deep Learning plays an important role in Industry 4.0 manufacturing lines and multiple ML-based image processing products are currently on the market. To be able to tackle a variety of problems where image acquisition is costly and time-consuming data generation is a promising approach. The proposed method only requires a handful of images for training, making it an ideal candidate for industrial application where data is scarce and confidential. It provides the foundation for a variety of use cases in the field of industrial Deep Learning. © 2020 IEEE.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
GANs
en_US
dc.subject
Generative modeling
en_US
dc.subject
Industrial
en_US
dc.subject
Images
en_US
dc.subject
Computer vision
en_US
dc.subject
Data augmentation
en_US
dc.subject
Small dataset
en_US
dc.subject
Industry 4.0
en_US
dc.title
Same Same but Different: Augmentation of Tiny Industrial Datasets using Generative Adversarial Networks
en_US
dc.type
Conference Paper
dc.date.published
2020-07-21
ethz.book.title
2020 7th Swiss Conference on Data Science (SDS)
en_US
ethz.pages.start
17
en_US
ethz.pages.end
22
en_US
ethz.event
7th Swiss Conference on Data Science (SDS 2020)
en_US
ethz.event.location
Online
en_US
ethz.event.date
June 26, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.identifier.scopus
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
ethz.date.deposited
2020-11-09T04:09:05Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2020-11-12T14:49:54Z
ethz.rosetta.lastUpdated
2021-02-15T20:43:04Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Same%20Same%20but%20Different:%20Augmentation%20of%20Tiny%20Industrial%20Datasets%20using%20Generative%20Adversarial%20Networks&rft.date=2020&rft.spage=17&rft.epage=22&rft.au=Ntavelis,%20Evangelos&Kastanis,%20Iason&Van%20Gool,%20Luc&Timofte,%20Radu&rft.isbn=978-1-7281-7177-7&978-1-7281-7178-4&rft.genre=proceeding&rft_id=info:doi/10.1109/SDS49233.2020.00011&rft.btitle=2020%207th%20Swiss%20Conference%20on%20Data%20Science%20(SDS)
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record