Heuristic Feedback for Generator Support in Generative Adversarial Network

Dawid Połap, Antoni Jaszcz

2024

Abstract

The possibilities of using generative adversarial networks (GANs) are enormous due to the possibility of generating new data that can deceive the classifier. The zero-sum game between two networks is a solution used on an increasingly large scale in today’s world. In this paper, we focus on expanding the model of generative adversarial networks by introducing a block with a selected heuristic algorithm. The additional block allows for creating a set of features extracted from the discriminator. The heuristic algorithm is based on the analysis of feature maps and extracting the position of selected pixels. Then they are clustered into averaged sets of features and used on created images by the generator. If the specified number of points within any set of features is higher than the threshold value, then the generator performs classical training. Otherwise, the loss function is subject to the penalty function. The proposed mechanism affects the operation of the GAN through additional sample analysis concerning containing specific features. To analyze the solution and impact of the proposed heuristic feedback, tests were performed based on known data sets.

Paper Citation

in Harvard Style

Połap D. and Jaszcz A. (2024). Heuristic Feedback for Generator Support in Generative Adversarial Network. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 862-869. DOI: 10.5220/0012405800003636

in Bibtex Style

@conference{icaart24,
author={Dawid Połap and Antoni Jaszcz},
title={Heuristic Feedback for Generator Support in Generative Adversarial Network},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={862-869},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012405800003636},
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 - Heuristic Feedback for Generator Support in Generative Adversarial Network
SN - 978-989-758-680-4
AU - Połap D.
AU - Jaszcz A.
PY - 2024
SP - 862
EP - 869
DO - 10.5220/0012405800003636
PB - SciTePress