Claim · model-written summary
Model parameter count fell to 1.46 M from 2.59 M.
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingQualifier
Verbatim
e0“the parameter count decreases from 2.59 M to 1.46 M, with the compression rate reaching 38.9%”
t0“tea leaf”
Title
Precise tea leaf disease detection using UAV low-altitude remote sensing and optimized YOLO11 model
Yaojun Zhang; Guiling Wu; Jianbo Shen PLoS ONE 2026. doi:10.1371/journal.pone.0342545
Other claims from this paper (4)
- Method / resource FCHE-YOLO improved tea disease detection mAP to 98.1% from 94.1% for YOLO11.
- Method / resource FCHE-YOLO inference speed rose to 47.5 FPS from 43.3 FPS.
- Method / resource Model FLOPs fell to 4.2 G from 6.4 G.
- Method / resource FCHE-YOLO reduced the missed detection rate in tea leaf disease testing.