LCIC-YOLO: A Lightweight Rice Pest Detection Network with Local–Context Complementary Representation and Independent Cooperative Gating

Rice pest detection in natural field images is affected by weak visual cues and interference from complex crop backgrounds. To improve the use of local appearance and surrounding contextual information, this study proposes LCIC-YOLO, a lightweight detector based on YOLO11n. An ICGSimConv module is introduced into the high-resolution P3 pathway to extract Local and Context features and regulate them independently using energy-based spatial responses before fusion. A six-class RP6 dataset containing 2637 images and 4312 annotated instances was curated from multiple public sources using duplicate detection and visual-family-based partitioning. Across three training seeds under the RP6 evaluation protocol, LCIC-YOLO achieved an mAP50 of 0.8826 ± 0.0051 and an mAP50--95 of 0.5902 ± 0.0047, with 2.60 M parameters and 6.57 GFLOPs. Its mean mAP50--95 exceeded YOLO11n by 2.67 percentage points. The control with matched gating and the fusion ablations support the contribution of Local information when integrated through branch-specific response estimation and independent Local–Context regulation. These results indicate that LCIC-YOLO improves the use of complementary spatial information while retaining the lightweight characteristics of the baseline detector.