Pill Metrics Learning with Multihead Attention

Richárd Rádli, Zsolt Vörösházi, László Czúni

2023

Abstract

In object recognition, especially, when new classes can easily appear during the application, few-shot learning has great importance. Metrics learning is an important elementary technique for few-shot object recognition which can be applied successfully for pill recognition. To enforce the exploitation of different object features we use multi-stream metrics learning networks for pill recognition in our article. We investigate the usage of multihead attention layers at different parts of the network. The performance is analyzed on two datasets with superior results to a state-of-the-art multi-stream pill recognition network.

Paper Citation

in Harvard Style

Rádli R., Vörösházi Z. and Czúni L. (2023). Pill Metrics Learning with Multihead Attention. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-671-2, SciTePress, pages 132-140. DOI: 10.5220/0012235500003598

in Bibtex Style

@conference{kdir23,
author={Richárd Rádli and Zsolt Vörösházi and László Czúni},
title={Pill Metrics Learning with Multihead Attention},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2023},
pages={132-140},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012235500003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Pill Metrics Learning with Multihead Attention
SN - 978-989-758-671-2
AU - Rádli R.
AU - Vörösházi Z.
AU - Czúni L.
PY - 2023
SP - 132
EP - 140
DO - 10.5220/0012235500003598
PB - SciTePress