Comparative Analysis of Supervised and Self-Supervised Transformer Models for Water Stress and Phytophthora Detection in Cupressus
Forests · 20.11.2026 · 17 (11) · 1393
DOI: 10.3390/f17111393 ↗Kurz gefasst
Fachartikel in der Zeitschrift Forests, online erschienen am 20.11.2026. Verfasst von Benjamín Luna-Benoso und 4 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Cupressus is a genus of conifers whose importance lies primarily in the ecological, environmental, and forestry fields. Therefore, it is important to maintain continuous monitoring of these species to promptly detect conditions such as water stress and infections caused by Phytophthora. In this work, a comparative analysis was carried out between supervised Transformer models (ViT-B/16 and Swin-Small) and self-supervised Transformer models (ViT-B/16+MAE, Swin-Base+SimMIM, ViT-B/14+DINOv2, and ViT-B/16+MaskFeat). Two experimental scenarios were considered. The first corresponds to clean data—that is, preprocessed and normalized images without additional degradations. The second corresponds to images incorporating noise in the form of visual perturbations via Gaussian blur, random adjust sharpness and color jitter, with the aim of evaluating and comparing the robustness of the models against image quality degradations. A model comparison was performed by evaluating performance using quantitative metrics such as accuracy, specificity, recall, precision, and F1-score. Additionally, a complementary analysis was conducted using confusion matrices, Receiver Operating Characteristic (ROC) curves, Precision–Recall (PR) curves, and activation maps obtained via Grad-CAM. The results show that the supervised Swin-Small model emerged as the best-performing model overall in both scenarios considered, obtaining an accuracy of 0.9969 in the clean data scenario and 0.7979 in the degraded data scenario. Meanwhile, ViT-B/16+MAE performed best among the self-supervised models, reaching an accuracy of 0.9962 in the clean data scenario and 0.7091 in the degraded data scenario. These results support the conclusion that Swin-Small, trained via supervised learning, offers the best balance between performance and robustness against visual degradations, whereas the evaluated self-supervised models failed to outperform the supervised approach under the analyzed conditions of this set of experiments.
Zitieren
APA
Luna-Benoso, B., Martínez-Perales, J. C., González-López, J. A., Morales-Rodríguez, Ú. S., & Pescador-Rojas, M. (2026). Comparative Analysis of Supervised and Self-Supervised Transformer Models for Water Stress and Phytophthora Detection in Cupressus. Forests, 17(11), 1393. https://doi.org/10.3390/f17111393
Vancouver
Luna-Benoso B, Martínez-Perales JC, González-López JA, Morales-Rodríguez ÚS, Pescador-Rojas M. Comparative Analysis of Supervised and Self-Supervised Transformer Models for Water Stress and Phytophthora Detection in Cupressus. Forests. 2026;17(11):1393. doi:10.3390/f17111393
BibTeX
@article{LunaBenoso2026,
author = {Luna-Benoso, Benjamín and Martínez-Perales, José Cruz and González-López, Josué Aldebaran and Morales-Rodríguez, Úrsula Samantha and Pescador-Rojas, Miriam},
title = {Comparative Analysis of Supervised and Self-Supervised Transformer Models for Water Stress and Phytophthora Detection in Cupressus},
journal = {Forests},
year = {2026},
volume = {17},
number = {11},
pages = {1393},
doi = {10.3390/f17111393}
}
EUVIMED