Show simple item record

dc.contributor.advisorReale, Michael, Chair
dc.contributor.advisorConfer, Amos
dc.contributor.advisorAndriamanalimanana, Bruno
dc.contributor.authorSchneider, Ethan H.
dc.date.accessioned2022-01-27T16:22:16Z
dc.date.available2022-01-27T16:22:16Z
dc.identifier.urihttp://hdl.handle.net/20.500.12648/7066
dc.description.abstractGANs developed to Translate an Image’s style between different domains often only care about the initial translation, and not the ability to further translate upon an image This can cause issues where, if one would want to generate upon an image and then further on, change that image even more that person may come into issues. This creates a ”gap” between the base images and the generated images, and in this paper a Multicyclic Loss is presented, where the Neural Network also trains on further translations to images that were already translated. iven_US
dc.language.isoen_USen_US
dc.subjectGenerative adversarial network (GAN)en_US
dc.subjectImage translationen_US
dc.subjectMulticyclic Lossen_US
dc.subjectNeural Networken_US
dc.titleMulticyclic Loss for Multidomain Image-to-Image Translationen_US
dc.typeMasters Projecten_US
dc.description.versionNAen_US
refterms.dateFOA2022-01-27T16:22:16Z
dc.description.institutionSUNY Polytechnic Instituteen_US
dc.description.departmentCollege of Engineeringen_US
dc.description.degreelevelMSen_US


Files in this item

Thumbnail
Name:
SCHNEIDER_PROJECT_FINAL_COPY.pdf
Size:
42.46Mb
Format:
PDF
Thumbnail
Name:
Library_Release.pdf
Size:
727.0Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record