Claim · model-written summary
Mean average precision at 0.5 rose 5.08% versus original YOLOv8s.
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingQualifier
Verbatim
e0“Compared to the original YOLOv8s model, mAP@0.5 increased by 5.08%”
t0“Tea”
Title
A YOLOv8‐based method for detecting tea disease in natural environments
Xiutong Li; Taiheng Zhang; Mei Yu; et al. Agronomy Journal 2025. doi:10.1002/agj2.70043
Other claims from this paper (5)
- Method / resource The proposed tea disease detector reached 96.34% mean average precision at 0.5.
- Method / resource The tea disease detector used 8.81 M parameters.
- Method / resource The tea disease detector required 20.3 G floating point operations.
- Method / resource Parameter count fell 26.14% versus original YOLOv8s.
- Method / resource Detection was fastest at 153.3 frames per second.