Unsupervised Latent Space Translation Network
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F20%3A00343432" target="_blank" >RIV/68407700:21240/20:00343432 - isvavai.cz</a>
Result on the web
<a href="https://www.esann.org/sites/default/files/proceedings/2020/ES2020-64.pdf" target="_blank" >https://www.esann.org/sites/default/files/proceedings/2020/ES2020-64.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Unsupervised Latent Space Translation Network
Original language description
One task that is often discussed in a computer vision is the mapping of an image from one domain to a corresponding image in another domain known as image-to-image translation. Currently there are several approaches solving this task. In this paper, we present an enhancement of the UNIT framework that aids in removing its main drawbacks. More specifically, we introduce an additional adversarial discriminator on the latent representation used instead of VAE, which enforces the latent space distributions of both domains to be similar. On MNIST and USPS domain adaptation tasks, this approach greatly outperforms competing approaches.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GA18-18080S" target="_blank" >GA18-18080S: Fusion-Based Knowledge Discovery in Human Activity Data</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ESANN 2020 - Proceedings
ISBN
978-2-87587-074-2
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
13-18
Publisher name
Ciaco - i6doc.com
Place of publication
Louvain la Neuve
Event location
Bruges
Event date
Oct 2, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—