GIWT-YOLO: an efficient multi-scale framework for real-time Scolytinae pests detection

Exploring foci of: Frontiers in Insect Science • Vol 5 GIWT-YOLO: an efficient multi-scale framework for real-time Scolytinae pests detection September 2025 • Jingwei Liu, Yongke Li, Lei Wang, Yunjie Zhao, Bowen Mao, Pengying Wang The broad range of Scolytinae pests sizes and their subtle visual similarities, especially in smaller species, continue to challenge the accuracy of mainstream object detection models. To address these challenges, this paper proposes GIWT-YOLO, a lightweight detection model based on YOLOv11s, specifically tailored for Scolytinae pests detection. (1) We designed a lightweight multi-scale convolution module, GIConv, to improve the model’s ability to extract features at different pest scales. This module enhances the… Open Article Page

National Institutional Ranking Framework The Myth Of The Framework Cynefin Framework Real-Time Strategy Django (Web Framework) Iran Nuclear Deal Framework United Nations Framework Convention On Climate Change Bootstrap (Front-End Framework) Real-Time Transport Protocol Open Article

Electron (Software Framework) Flask (Web Framework) Efficient-Market Hypothesis Metal–Organic Framework The Open Group Architecture Framework Real-Time Kinematic Positioning Real-Time Polymerase Chain Reaction Real-Time Clock Australian Qualifications Framework Open Article

Risk Management Framework Department Of Defense Architecture Framework Enterprise Architecture Framework Efficient Frontier Business Process Framework (Etom) Kivy (Framework) Open Article