{"user_id":"245736","language":[{"iso":"eng"}],"doi":"10.5220/0011727900003411","department":[{"_id":"102"}],"page":"418-425","type":"conference","publication_identifier":{"isbn":["978-989-758-626-2"]},"title":"Metric-Based Few-Shot Learning for Pollen Grain Image Classification","citation":{"short":"P. Viertel, M. König, J. Rexilius, in: M. De Marsico, G. Sanniti di Baja, A. Fred (Eds.), Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM, 2023, pp. 418–425.","ama":"Viertel P, König M, Rexilius J. Metric-Based Few-Shot Learning for Pollen Grain Image Classification. In: De Marsico M, Sanniti di Baja G, Fred A, eds. Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM. ; 2023:418-425. doi:10.5220/0011727900003411","mla":"Viertel, Philipp, et al. “Metric-Based Few-Shot Learning for Pollen Grain Image Classification.” Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM, edited by Maria De Marsico et al., 2023, pp. 418–25, doi:10.5220/0011727900003411.","bibtex":"@inproceedings{Viertel_König_Rexilius_2023, title={Metric-Based Few-Shot Learning for Pollen Grain Image Classification}, DOI={10.5220/0011727900003411}, booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM}, author={Viertel, Philipp and König, Matthias and Rexilius, Jan}, editor={De Marsico, Maria and Sanniti di Baja, Gabriella and Fred , AnaEditors}, year={2023}, pages={418–425} }","apa":"Viertel, P., König, M., & Rexilius, J. (2023). Metric-Based Few-Shot Learning for Pollen Grain Image Classification. In M. De Marsico, G. Sanniti di Baja, & A. Fred (Eds.), Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM (pp. 418–425). Lisbon, Portugal. https://doi.org/10.5220/0011727900003411","chicago":"Viertel, Philipp, Matthias König, and Jan Rexilius. “Metric-Based Few-Shot Learning for Pollen Grain Image Classification.” In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM, edited by Maria De Marsico, Gabriella Sanniti di Baja, and Ana Fred , 418–25, 2023. https://doi.org/10.5220/0011727900003411.","ieee":"P. Viertel, M. König, and J. Rexilius, “Metric-Based Few-Shot Learning for Pollen Grain Image Classification,” in Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM, Lisbon, Portugal, 2023, pp. 418–425.","alphadin":"Viertel, Philipp ; König, Matthias ; Rexilius, Jan: Metric-Based Few-Shot Learning for Pollen Grain Image Classification. In: De Marsico, M. ; Sanniti di Baja, G. ; Fred , A. (Hrsg.): Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM, 2023, S. 418–425"},"editor":[{"full_name":"De Marsico, Maria ","last_name":"De Marsico","first_name":"Maria "},{"full_name":"Sanniti di Baja, Gabriella ","last_name":"Sanniti di Baja","first_name":"Gabriella "},{"full_name":"Fred , Ana","last_name":"Fred ","first_name":"Ana"}],"quality_controlled":"1","_id":"2292","year":"2023","date_updated":"2025-10-10T12:15:14Z","date_created":"2023-01-09T09:05:03Z","status":"public","author":[{"orcid":"0000-0002-7274-4290","full_name":"Viertel, Philipp","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-7274-4290/work/181737429","first_name":"Philipp","last_name":"Viertel","id":"216274"},{"id":"213498","last_name":"König","first_name":"Matthias","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-4915-0750/work/181737430","full_name":"König, Matthias","orcid":"0000-0002-4915-0750"},{"orcid":"0000-0002-4579-214X","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-4579-214X/work/181737431","full_name":"Rexilius, Jan","last_name":"Rexilius","id":"245736","first_name":"Jan"}],"conference":{"location":"Lisbon, Portugal","end_date":"2023-02-24","name":"12th International Conference on Pattern Recognition Applications and Methods","start_date":"2023-02-22"},"publication_status":"published","publication":"Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM","abstract":[{"lang":"eng","text":"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 accura cy 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. "}]}