Latent Code Disentanglement Using Orthogonal Latent Codes and Inter-Domain Signal Transformation

Babak Solhjoo, Emanuele Rodolà

2023

Abstract

Auto Encoders are specific types of Deep Neural Networks that extract latent codes in a lower dimensional space for the inputs that are expressed in the higher dimensions. These latent codes are extracted by forcing the network to generate similar outputs to the inputs while limiting the data that can flow through the network in the latent space by choosing a lower dimensional space (Bank et al., 2020). Variational Auto Encoders realize a similar objective by generating a distribution of the latent codes instead of deterministic latent codes (Cosmo et al., 2020). This work focuses on generating semi-orthogonal variational latent codes for the inputs from different source types such as voice, image, and text for the same objects. The novelty of this work is on aiming to obtain unified variational latent codes for different manifestations of the same objects in the physical world using orthogonal latent codes. In order to achieve this objective, a specific Loss Function has been introduced to generate semi-orthogonal and variational latent codes for different objects. Then these orthogonal codes have also been exploited to map different manifestations of the same objects to each other. This work also uses these codes to convert the manifestations from one domain to another one.

Download


Paper Citation


in Harvard Style

Solhjoo B. and Rodolà E. (2023). Latent Code Disentanglement Using Orthogonal Latent Codes and Inter-Domain Signal Transformation. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-623-1, pages 427-436. DOI: 10.5220/0011860200003393


in Bibtex Style

@conference{icaart23,
author={Babak Solhjoo and Emanuele Rodolà},
title={Latent Code Disentanglement Using Orthogonal Latent Codes and Inter-Domain Signal Transformation},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2023},
pages={427-436},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011860200003393},
isbn={978-989-758-623-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Latent Code Disentanglement Using Orthogonal Latent Codes and Inter-Domain Signal Transformation
SN - 978-989-758-623-1
AU - Solhjoo B.
AU - Rodolà E.
PY - 2023
SP - 427
EP - 436
DO - 10.5220/0011860200003393