Spatial-aware lightweight network for real-time tea disease detection: A coordinate attention-enhanced YOLOv8n approach with path-decoupling strategy

Xiang Lyu, Yue Yu, ChengLei Song · 2026

Read Spatial-aware lightweight network for real-time tea disease detection: A coordinate attention-enhanced YOLOv8n approach with path-decoupling strategy by Xiang Lyu, Yue Yu, ChengLei Song (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354583.txt.

Description

Lyu and colleagues, in a 2026 paper, build a leaner vision model that spots tea leaf diseases in real time. Diseased leaves cut tea quality and yield, but the best detection models are too heavy for the small computers farms can run in the field. Their design trims a popular detection model and adds a trick that sharpens its sense of where things are.

The trimmed model sheds about a third of its parts and a quarter of its computing work. It also gains an attention step that weighs the position of features, helping it catch faint disease marks. On test images it scored near the top for detection accuracy, beating the untrimmed starting model. The team plugged it into a working service that writes reports on its own and runs on ordinary processors. They present it as proof that accurate crop checks can run on cheap hardware.

Catalog record

CREATORXiang Lyu, Yue Yu, ChengLei Song
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE52098
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0354583

Browse the full library · About the Tower of Babel