Conjugate Gradient for Latent Space Manipulation

Walid Messaoud, Rim Trabelsi, Adnane Cabani, Fatma Abdelkefi

2024

Abstract

Generative Adversarial Networks (GANs) have revolutionized image generation, allowing the production of high-quality images from latent codes in the latent space. However, manipulating the latent space to achieve specific image attributes remains challenging. Existing methods often lack disentanglement, leading to unintended changes in other attributes. Moreover, most of the existing techniques are limited to one-dimensional conditioning, making them less effective for complex multidimensional modifications. In this paper, we propose a novel approach that combines an auxiliary map composed of convolutional layers and Conjugate Gradient (CG) to enhance latent space manipulation. The proposed auxiliary map provides a versatile and expressive way to incorporate external information for image generation, while CG facilitates precise and controlled manipulations. Our experimental results demonstrate better performance compared to state-of-the-art methods.

Paper Citation

in Harvard Style

Messaoud W., Trabelsi R., Cabani A. and Abdelkefi F. (2024). Conjugate Gradient for Latent Space Manipulation. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 50-57. DOI: 10.5220/0012268700003636

in Bibtex Style

@conference{icaart24,
author={Walid Messaoud and Rim Trabelsi and Adnane Cabani and Fatma Abdelkefi},
title={Conjugate Gradient for Latent Space Manipulation},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={50-57},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012268700003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Conjugate Gradient for Latent Space Manipulation
SN - 978-989-758-680-4
AU - Messaoud W.
AU - Trabelsi R.
AU - Cabani A.
AU - Abdelkefi F.
PY - 2024
SP - 50
EP - 57
DO - 10.5220/0012268700003636
PB - SciTePress