Learning Centre

Pioneer Networks

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Heljakka, Ari
dc.contributor.author Solin, Arno
dc.contributor.author Kannala, Juho
dc.contributor.editor Mori, Greg
dc.contributor.editor Jawahar, C.V.
dc.contributor.editor Schindler, Konrad
dc.contributor.editor Li, Hongdong
dc.date.accessioned 2019-06-20T13:14:01Z
dc.date.available 2019-06-20T13:14:01Z
dc.date.issued 2019
dc.identifier.citation Heljakka , A , Solin , A & Kannala , J 2019 , Pioneer Networks : Progressively Growing Generative Autoencoder . in G Mori , C V Jawahar , K Schindler & H Li (eds) , Computer Vision – ACCV 2018 - 14th Asian Conference on Computer Vision, Revised Selected Papers . Lecture notes in computer science , vol. 11361 , SPRINGER , Springer, Cham , pp. 22-38 , Asian Conference on Computer Vision , Perth , Australia , 02/12/2018 . https://doi.org/10.1007/978-3-030-20887-5_2 en
dc.identifier.isbn 978-3-030-20886-8
dc.identifier.isbn Online ISBN 978-3-030-20887-5
dc.identifier.issn 1611-3349
dc.identifier.other PURE UUID: 68b6dc32-099f-49d4-996f-f47af6001c0e
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/pioneer-networks(68b6dc32-099f-49d4-996f-f47af6001c0e).html
dc.identifier.other PURE LINK: http://www.scopus.com/inward/record.url?scp=85066805190&partnerID=8YFLogxK
dc.identifier.other PURE LINK: http://arxiv.org/abs/1807.03026
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/33778899/SCI_Heljakka_et_al_Pioneer_Networks_ACCV.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/38827
dc.description.abstract We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, but they cannot reconstruct existing images. Previous works have attempted to extend GANs to support such inference but, so far, have not delivered satisfactory high-quality results. Instead, we propose the Progressively Growing Generative Autoencoder (Pioneer) network which achieves high-quality reconstruction with images without requiring a GAN discriminator. We merge recent techniques for progressively building up the parts of the network with the recently introduced adversarial encoder–generator network. The ability to reconstruct input images is crucial in many real-world applications, and allows for precise intelligent manipulation of existing images. We show promising results in image synthesis and inference, with state-of-the-art results in CelebA inference tasks. en
dc.format.extent 22-38
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher Springer Nature
dc.relation.ispartof Asian Conference on Computer Vision en
dc.relation.ispartofseries Computer Vision – ACCV 2018 en
dc.relation.ispartofseries Lecture notes in computer science en
dc.relation.ispartofseries Volume 11361 en
dc.rights openAccess en
dc.subject.other Theoretical Computer Science en
dc.subject.other Computer Science(all) en
dc.subject.other 113 Computer and information sciences en
dc.title Pioneer Networks en
dc.type A4 Artikkeli konferenssijulkaisussa fi
dc.description.version Peer reviewed en
dc.contributor.department Department of Computer Science
dc.subject.keyword Autoencoder
dc.subject.keyword Computer vision
dc.subject.keyword Generative models
dc.subject.keyword Theoretical Computer Science
dc.subject.keyword Computer Science(all)
dc.subject.keyword 113 Computer and information sciences
dc.identifier.urn URN:NBN:fi:aalto-201906203893
dc.identifier.doi 10.1007/978-3-030-20887-5_2
dc.type.version acceptedVersion

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication