Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

EM-LAST: Effective Multidimensional Latent Space Transport for an Unpaired Image-to-Image Translation With an Energy-Based Modelopen access

Authors
Han, GiwoongMin, JinhongHan, Sung Won
Issue Date
2022
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Aerospace electronics; Decoding; Deep learning; Energy-based model; Generative adversarial networks; Langevin dynamics; Licenses; Task analysis; Visualization; image-to-image translation; multidimensional latent space; vector-quantized variational autoencoder
Citation
IEEE ACCESS, v.10, pp.72839 - 72849
Indexed
SCIE
SCOPUS
Journal Title
IEEE ACCESS
Volume
10
Start Page
72839
End Page
72849
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/144179
DOI
10.1109/ACCESS.2022.3189352
ISSN
2169-3536
Abstract
For an unpaired image-to-image translation to work effectively, the latent space of each image domain must be well-designed. The codes of each style must be translated toward the target while preserving the parts corresponding to the source content. In general, most Variational Autoencoder (VAE)-based models use a one-dimensional latent space. However, to apply high dimensional methodologies such as vector quantization, controlling a multidimensional latent space is necessary. In this study, among the VAE-based models that use relatively complex multidimensional latent spaces, we apply an Energy-Based Model and Vector-Quantized VAE v2, with the latter as the main model. We show that among the latent spaces that represent each image domain, the importance of each feature at the top and bottom latent spaces must be interpreted differently for appropriate translation. Therefore, we argue that simply understanding the features of latent space composition well can show effective image translation results. We also present various analyses and visual outcomes of multidimensional latent space transport.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Industrial and Management Engineering > 1. Journal Articles

qrcode

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

Related Researcher

Researcher Han, Sung Won photo

Han, Sung Won
공과대학 (산업경영공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE