Few-Shot Learning for Strawberry Variety Classification: A Prototypical Network-Based Approach
Firat University Journal of Experimental and Computational Engineering · 27.06.2026 · 5 (2) · 454-467
DOI: 10.62520/fujece.1925239 ↗Kurz gefasst
Fachartikel in der Zeitschrift Firat University Journal of Experimental and Computational Engineering, online erschienen am 27.06.2026. Verfasst von Esra Yüce und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben.
Abstract (Originalsprache)
Classification of different types of strawberries is an essential problem in agriculture and quality control; however, it presents a challenge to traditional deep learning solutions because of the need for large-scale labeled datasets. In this research, a few-shot learning (FSL) model based on Prototypical Networks was applied to classify four different commercial types of strawberries (A, B, C, and Jumbo), utilizing the Mendeley Strawberry Grading Dataset that includes only 103 labeled images for training. A unique pipeline for training an FSL model was created through a combination of warm-up pre-training, differential learning rate strategy, and 4-way 5-shot episodic training; two backbones (ResNet50 and EfficientNet-B0) were compared under a 5-fold stratified cross-validation. While ResNet50 obtained test accuracy, macro F1-score, and Cohen's Kappa equal to 99.00%, 99.11%, and 98.62% respectively, EfficientNet-B0 achieved 98.00%, 98.33%, and 97.30%. Both models produced an AUC value of 99.80%. Interpretability analysis utilizing GradCAM++ showed that both networks focused on relevant areas of the fruits. This research proved that metric-based few-shot learning can be used successfully as an alternative solution to traditional deep learning methods in case of scarce datasets of agricultural images.
Zitieren
APA
Yüce, E., Şahin, M. E., Ulutaş, H., Karakuş, M. Ö., & Er, O. (2026). Few-Shot Learning for Strawberry Variety Classification: A Prototypical Network-Based Approach. Firat University Journal of Experimental and Computational Engineering, 5(2), 454-467. https://doi.org/10.62520/fujece.1925239
Vancouver
Yüce E, Şahin ME, Ulutaş H, Karakuş MÖ, Er O. Few-Shot Learning for Strawberry Variety Classification: A Prototypical Network-Based Approach. Firat University Journal of Experimental and Computational Engineering. 2026;5(2):454-467. doi:10.62520/fujece.1925239
BibTeX
@article{Yce2026,
author = {Yüce, Esra and Şahin, Muhammet Emin and Ulutaş, Hasan and Karakuş, Mücella Özbay and Er, Orhan},
title = {Few-Shot Learning for Strawberry Variety Classification: A Prototypical Network-Based Approach},
journal = {Firat University Journal of Experimental and Computational Engineering},
year = {2026},
volume = {5},
number = {2},
pages = {454--467},
doi = {10.62520/fujece.1925239}
}
EUVIMED