Enhancing Computer Vision with Knowledge: a Rummikub Case Study

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Vandevelde, Simon, Mertens, Laurent, Lauwers, Sverre, Vennekens, Joost
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909406386454528
author Vandevelde, Simon
Mertens, Laurent
Lauwers, Sverre
Vennekens, Joost
author_facet Vandevelde, Simon
Mertens, Laurent
Lauwers, Sverre
Vennekens, Joost
contents Artificial Neural Networks excel at identifying individual components in an image. However, out-of-the-box, they do not manage to correctly integrate and interpret these components as a whole. One way to alleviate this weakness is to expand the network with explicit knowledge and a separate reasoning component. In this paper, we evaluate an approach to this end, applied to the solving of the popular board game Rummikub. We demonstrate that, for this particular example, the added background knowledge is equally valuable as two-thirds of the data set, and allows to bring down the training time to half the original time.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18172
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Computer Vision with Knowledge: a Rummikub Case Study
Vandevelde, Simon
Mertens, Laurent
Lauwers, Sverre
Vennekens, Joost
Computer Vision and Pattern Recognition
Logic in Computer Science
Artificial Neural Networks excel at identifying individual components in an image. However, out-of-the-box, they do not manage to correctly integrate and interpret these components as a whole. One way to alleviate this weakness is to expand the network with explicit knowledge and a separate reasoning component. In this paper, we evaluate an approach to this end, applied to the solving of the popular board game Rummikub. We demonstrate that, for this particular example, the added background knowledge is equally valuable as two-thirds of the data set, and allows to bring down the training time to half the original time.
title Enhancing Computer Vision with Knowledge: a Rummikub Case Study
topic Computer Vision and Pattern Recognition
Logic in Computer Science
url https://arxiv.org/abs/2411.18172