Ajou University repository

Improving Learning time in Unsupervised Image-To-Image Translation
Citations

SCOPUS

0

Citation Export

Publication Year
2019-03-18
Journal
1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019, pp.455-458
Keyword
CNNdeep learningDiscoGANGAN
Mesh Keyword
Big changesDiscoGANHigh quality imagesImage translationImproving learningLocal TextureShape changeUp sampling
All Science Classification Codes (ASJC)
Electrical and Electronic EngineeringComputer Science ApplicationsArtificial Intelligence
Abstract
Unsupervised image-To-image translation can map local textures between two domains, but typically fails when the domain requires big shape changes. It is difficult to learn how to make such big change using the basic convolution layer, and furthermore it takes much time to learn. For faster learning and high-quality image generation, we propose to use Cycle GAN that is combined with Resnet in a network that is connected with the residual block for upsampling to make big shape change and construct faster image-To-image translation.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36436
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85063908136&origin=inward
DOI
https://doi.org/10.1109/icaiic.2019.8669076
Journal URL
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8665865
Type
Conference
Funding
ACKNOWLEDGMENT \This research was supported by the MIST(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW supervised by the IITP(Institute for Information & communications Technology Promotion)\ (2015-0-00908)
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Choi, Youngjune Image
Choi, Youngjune최영준
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.