Show simple item record

dc.contributor.authorKlein, Jonathan
dc.contributor.authorPirk, Sören
dc.contributor.authorMichels, Dominik L.
dc.date.accessioned2020-12-02T11:34:19Z
dc.date.available2020-12-02T11:34:19Z
dc.date.issued2020-06-16
dc.identifier.urihttp://hdl.handle.net/10754/666238
dc.description.abstractWe present a novel domain adaptation framework that uses morphologic segmentation to translate images from arbitrary input domains (real and synthetic) into a uniform output domain. Our framework is based on an established image-to-image translation pipeline that allows us to first transform the input image into a generalized representation that encodes morphology and semantics - the edge-plus-segmentation map (EPS) - which is then transformed into an output domain. Images transformed into the output domain are photo-realistic and free of artifacts that are commonly present across different real (e.g. lens flare, motion blur, etc.) and synthetic (e.g. unrealistic textures, simplified geometry, etc.) data sets. Our goal is to establish a preprocessing step that unifies data from multiple sources into a common representation that facilitates training downstream tasks in computer vision. This way, neural networks for existing tasks can be trained on a larger variety of training data, while they are also less affected by overfitting to specific data sets. We showcase the effectiveness of our approach by qualitatively and quantitatively evaluating our method on four data sets of simulated and real data of urban scenes. Additional results can be found on the project website available at http://jonathank.de/research/eps/ .
dc.description.sponsorshipThis work has been supported by KAUST under individual baseline funding.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2006.09322
dc.rightsArchived with thanks to arXiv
dc.titleDomain Adaptation with Morphologic Segmentation
dc.typePreprint
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentComputer Science Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.eprint.versionPre-print
dc.contributor.institutionUniversity of Bonn
dc.contributor.institutionGoogle Brain
dc.identifier.arxivid2006.09322
kaust.personMichels, Dominik L.
refterms.dateFOA2020-12-02T11:34:53Z
kaust.acknowledged.supportUnitBaseline Funding


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
3.634Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record