Metric-Based Few-Shot Learning for Pollen Grain Image Classification

Philipp Viertel, Matthias König, Jan Rexilius

2023

Abstract

Pollen is an important substance produced by seed plants. They contain the male gametes which are necessary for fertilization and the reproduction of flowering plants. The scientific study of pollen, palynology, plays a crucial role in a number of disciplines, such as allergology, ecology, forensics, as well as food-production. Current trends in climate research indicate an increasing importance of palynology, partly due to a projected rise in allergies. Pollen detection and classification in microscopic images via deep neural networks has been studied and researched, however, pollen data is often sparse or imbalanced, especially when compared to the number of plant species, which is estimated to be between 330,000 and 450,000, of which only a small percentage is investigated. In this work, we present a solution that does not require a large number of data samples by employing Few-Shot Learning. Our work shows, that by utilizing Prototypical Networks, an average classification accuracy of 90% can be achieved on state-of-the-art pollen data sets. The results can be further improved by fine-tuning the net, achieving up to 98% accuracy on novel classes. To our best knowledge, this is the first attempt at applying Few-Shot Learning in the field of pollen analysis.

Download


Paper Citation


in Harvard Style

Viertel P., König M. and Rexilius J. (2023). Metric-Based Few-Shot Learning for Pollen Grain Image Classification. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 418-425. DOI: 10.5220/0011727900003411


in Bibtex Style

@conference{icpram23,
author={Philipp Viertel and Matthias König and Jan Rexilius},
title={Metric-Based Few-Shot Learning for Pollen Grain Image Classification},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={418-425},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011727900003411},
isbn={978-989-758-626-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Metric-Based Few-Shot Learning for Pollen Grain Image Classification
SN - 978-989-758-626-2
AU - Viertel P.
AU - König M.
AU - Rexilius J.
PY - 2023
SP - 418
EP - 425
DO - 10.5220/0011727900003411