CuFormer U-Net: a transformer-enhanced multi-task network for cucumber leaf disease detection and segmentation
- 1Laboratory of Mechanics of Robots and Manipulators, Joldasbekov Institute of Mechanics and Engineering
- 2Department of Mathematical and Computer Modeling, International Information Technology University
Abstract
Cucumber foliar symptoms reduce functional leaf area and complicate greenhouse scouting. This study presents CuFormer U-Net, a Transformer-enhanced multi-task network for three-class image-level classification on the 3,754-image Kaggle benchmark (healthy, powdery mildew, and downy mildew) and binary visible-symptom segmentation on a separate 400-image greenhouse cohort (200 healthy and 200 affected leaves). The greenhouse annotations comprise 2,705 rectangles (1,741 color-abnormality and 964 tissue-damage instances); rectangle-seeded lesion masks were manually refined for the dense-prediction experiments. The reported fixed-split point estimates were 96.7% accuracy, 96.3% macro precision, 95.8% macro recall, and 96.0% macro F1 for classification, and 92.4% mean image-wise Dice, 83.1% macro IoU, 93.2% foreground precision, and 91.7% foreground recall for segmentation. The complete internal-validation ablation configuration reached 93.1% Dice and 87.3% IoU. The available experiment archive does not contain independent-seed reruns, per-image predictions for inferential testing, annotator-level masks, quantitative results for the separate 100-image greenhouse stress-test cohort, or reproducible hardware profiling. Accordingly, all between-model differences are interpreted descriptively, the external cohort is not presented as formal external validation, and robustness and deployment claims have been moderated. CuFormer U-Net provides a technically motivated basis for joint recognition and spatial characterization, but confirmatory multi-run and multi-site evaluation is required.
boundary refinement, cucumber leaf disease, multi-task learning, plant disease, precision agriculture, semantic segmentation, vision transformer
Related
- SportRGDET: Scene prior and relation graph enhanced detection transformer for sports scenes
- Combined application of bacterial biofertilizers, seaweed, and Thymbra spicata extract enhanced productivity, nutritional value, and postharvest shelf life of cucumber (Cucumis sativus L.).
- An annotated cucumber leaf image dataset for detection of visible damage and abnormal color symptoms in complex cultivation environments
- GAMPoint: Geometry-augmented vision transformer with a multimodal-ready interface for 3D point-cloud segmentation
- MaxCAT-Net: Hybrid Transformer-Based Skin Lesion Classification and Lightweight Segmentation with Calibration and Cross-Dataset Validation
BibTeX
@article{omarov2026cuformer,
title = {{CuFormer U-Net: a transformer-enhanced multi-task network for cucumber leaf disease detection and segmentation}},
author = {Batyrkhan Omarov and Sayat Ibrayev and Nurbibi Imanbayeva},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1975030},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1975030/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - CuFormer U-Net: a transformer-enhanced multi-task network for cucumber leaf disease detection and segmentation
AU - Batyrkhan Omarov
AU - Sayat Ibrayev
AU - Nurbibi Imanbayeva
PY - 2026
DA - 2026/10/07
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1975030
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1975030/full
AB - Cucumber foliar symptoms reduce functional leaf area and complicate greenhouse scouting. This study presents CuFormer U-Net, a Transformer-enhanced multi-task network for three-class image-level classification on the 3,754-image Kaggle benchmark (healthy, powdery mildew, and downy mildew) and binary visible-symptom segmentation on a separate 400-image greenhouse cohort (200 healthy and 200 affected leaves). The greenhouse annotations comprise 2,705 rectangles (1,741 color-abnormality and 964 tissue-damage instances); rectangle-seeded lesion masks were manually refined for the dense-prediction experiments. The reported fixed-split point estimates were 96.7% accuracy, 96.3% macro precision, 95.8% macro recall, and 96.0% macro F1 for classification, and 92.4% mean image-wise Dice, 83.1% macro IoU, 93.2% foreground precision, and 91.7% foreground recall for segmentation. The complete internal-validation ablation configuration reached 93.1% Dice and 87.3% IoU. The available experiment archive does not contain independent-seed reruns, per-image predictions for inferential testing, annotator-level masks, quantitative results for the separate 100-image greenhouse stress-test cohort, or reproducible hardware profiling. Accordingly, all between-model differences are interpreted descriptively, the external cohort is not presented as formal external validation, and robustness and deployment claims have been moderated. CuFormer U-Net provides a technically motivated basis for joint recognition and spatial characterization, but confirmatory multi-run and multi-site evaluation is required. boundary refinement, cucumber leaf disease, multi-task learning, plant disease, precision agriculture, semantic segmentation, vision transformer
SN - 1664-462X
ER -