dc.contributor.author
Sixt, Leon
dc.contributor.author
Wild, Benjamin
dc.contributor.author
Landgraf, Tim
dc.date.accessioned
2018-07-10T14:45:21Z
dc.date.available
2018-07-10T14:45:21Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/22442
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-251
dc.description.abstract
Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting. The costs of annotating data manually can render the use of DCNNs infeasible. We present a novel framework called RenderGAN that can generate large amounts of realistic, labeled images by combining a 3D model and the Generative Adversarial Network framework. In our approach, image augmentations (e.g., lighting, background, and detail) are learned from unlabeled data such that the generated images are strikingly realistic while preserving the labels known from the 3D model. We apply the RenderGAN framework to generate images of barcode-like markers that are attached to honeybees. Training a DCNN on data generated by the RenderGAN yields considerably better performance than training it on various baselines.
en
dc.format.extent
9 Seiten
de_DE
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
de_DE
dc.subject
generative adversarial networks
en
dc.subject
unsupervised learning
en
dc.subject
social insects
en
dc.subject
deep learning
en
dc.subject.ddc
500 Naturwissenschaften und Mathematik::590 Tiere (Zoologie)::595 Arthropoden (Gliederfüßer)
de_DE
dc.subject.ddc
000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::004 Datenverarbeitung; Informatik
de_DE
dc.title
RenderGAN: Generating Realistic Labeled Data
de_DE
dc.type
Wissenschaftlicher Artikel
de_DE
dcterms.bibliographicCitation.articlenumber
66
dcterms.bibliographicCitation.doi
10.3389/frobt.2018.00066
dcterms.bibliographicCitation.journaltitle
Frontiers in Robotics and AI
dcterms.bibliographicCitation.volume
5
dcterms.bibliographicCitation.url
https://doi.org/10.3389/frobt.2018.00066
de_DE
refubium.affiliation
Mathematik und Informatik
de_DE
refubium.affiliation.other
Institut für Informatik
![Confidence was never recorded for this value](/cache_202e45ad85b55efaeb29160f63cd3f3b/themes/FuCD/images/authority_control/invisible.gif)
de_DE
refubium.funding
Institutional Participation
refubium.funding.id
Frontiers
refubium.note.author
Der Artikel wurde in einer reinen Open-Access-Zeitschrift publiziert.
de_DE
refubium.resourceType.isindependentpub
no
de_DE
dcterms.accessRights.openaire
open access
dcterms.isPartOf.issn
2296-9144