loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Andreas Meißner 1 ; 2 ; 1 and Michaela Geierhos 2

Affiliations: 1 Zentrale Stelle für Informationstechnik im Sicherheitsbereich, Zamdorfer Straße 88, 81677 Munich, Germany ; 2 Research Institute CODE, Bundeswehr University Munich, Carl-Wery-Straße 22, Munich, Germany

Keyword(s): Latent Space Editing, Semantic Image Editing, Generative Adversarial Networks, StyleGAN, Local Search.

Abstract: Semantic image editing allows users to selectively change entire image attributes in a controlled manner with just a few clicks. Most approaches use a generative adversarial network (GAN) for this task to learn an appropriate latent space representation and attribute-specific transformations. While earlier approaches often suffer from entangled attribute manipulations, newer ones improve on this aspect by using separate specialized networks for attribute extraction. Iterative optimization algorithms based on backpropagation constitute a possible approach to find attribute vectors with little entanglement. However, this requires a large amount of GPU memory, training instabilities can occur, and the used models have to be differentiable. To address these issues, we propose a local search-based approach for latent space editing. We show that it performs at the same level as previous algorithms and avoids these drawbacks.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.224.55.63

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Meißner, A.; Fröhlich, A. and Geierhos, M. (2022). Keep It Simple: Local Search-based Latent Space Editing. In Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - NCTA; ISBN 978-989-758-611-8; ISSN 2184-3236, SciTePress, pages 273-283. DOI: 10.5220/0011524700003332

@conference{ncta22,
author={Andreas Meißner. and Andreas Fröhlich. and Michaela Geierhos.},
title={Keep It Simple: Local Search-based Latent Space Editing},
booktitle={Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - NCTA},
year={2022},
pages={273-283},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011524700003332},
isbn={978-989-758-611-8},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - NCTA
TI - Keep It Simple: Local Search-based Latent Space Editing
SN - 978-989-758-611-8
IS - 2184-3236
AU - Meißner, A.
AU - Fröhlich, A.
AU - Geierhos, M.
PY - 2022
SP - 273
EP - 283
DO - 10.5220/0011524700003332
PB - SciTePress