WSD-YOLO: A lightweight YOLO-based model with enhanced feature representation for maize pest detection
- 1School of Software, Henan University, Kaifeng, China
- 2School of Computer and Information Engineering, Henan University, Kaifeng, China
Abstract
As a major staple crop with global significance, maize is highly vulnerable to pest infestations throughout its growth cycle, which can substantially limit plant development and reduce yield. In practice, accurate detection remains challenging due to pronounced morphological variations across pest life stages, as well as interference from complex field backgrounds, often leading to missed detections. To address these challenges, we propose WSD-YOLO (YOLOv11n with WindmillConv, Single-Scale High-Level Transformer, and Dual-Attention Weighted Aggregation), a high-accuracy maize pest detection model built upon an improved YOLOv11n framework. The WindmillConv (WMConv) module enhances the model’s sensitivity to multi-directional pest textures, thereby improving low-level feature representation while maintaining a lightweight convolutional design. At a deeper level, the Single-Scale High-Level Transformer (SHLT) introduces global self-attention, enabling effective suppression of background noise with minimal computational overhead. In addition, the Dual-Attention Weighted Aggregation (DAWA) module adaptively fuses same-scale features, improving the detection of pests with diverse morphological characteristics. Experimental results from three repeated training runs (random seeds: 42, 2026, 3407) on the IPMaize dataset demonstrate that the proposed method achieves an averaged [email protected] of 78.77% (79.7% with seed = 42) and averaged [email protected]:0.95 of 52.63%. Cross-dataset evaluations on the Tomato Pest&Diseases and IP102 datasets further confirm the model’s strong generalization capability.
Related
- Stage-wise collaborative feature enhancement for accurate maize insect pest detection in complex agricultural scenes
- ISD-YOLO: A lightweight and efficient feature extraction network for invoice seal detection
- Dual-domain self-supervised feature alignment via spectral–spatial representation learning for deepfake anomaly detection
- Cross-level attention and lightweight feature extraction for improved tomato ripeness detection in complex greenhouse environments
- CGW-DETR: a multi-scale feature enhanced RT-DETR Qianxi cherry tomato maturity detection model for dense small targets
BibTeX
@article{qu2026wsdyolo,
title = {{WSD-YOLO: A lightweight YOLO-based model with enhanced feature representation for maize pest detection}},
author = {Shenming Qu and Zhiheng Liu and Huazhen Zhao and Yichao Wu and Yang Yang},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0357034},
url = {https://doi.org/10.1371/journal.pone.0357034},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - WSD-YOLO: A lightweight YOLO-based model with enhanced feature representation for maize pest detection
AU - Shenming Qu
AU - Zhiheng Liu
AU - Huazhen Zhao
AU - Yichao Wu
AU - Yang Yang
PY - 2026
DA - 2026/09/15
JO - PLOS One
DO - 10.1371/journal.pone.0357034
UR - https://doi.org/10.1371/journal.pone.0357034
AB - As a major staple crop with global significance, maize is highly vulnerable to pest infestations throughout its growth cycle, which can substantially limit plant development and reduce yield. In practice, accurate detection remains challenging due to pronounced morphological variations across pest life stages, as well as interference from complex field backgrounds, often leading to missed detections. To address these challenges, we propose WSD-YOLO (YOLOv11n with WindmillConv, Single-Scale High-Level Transformer, and Dual-Attention Weighted Aggregation), a high-accuracy maize pest detection model built upon an improved YOLOv11n framework. The WindmillConv (WMConv) module enhances the model’s sensitivity to multi-directional pest textures, thereby improving low-level feature representation while maintaining a lightweight convolutional design. At a deeper level, the Single-Scale High-Level Transformer (SHLT) introduces global self-attention, enabling effective suppression of background noise with minimal computational overhead. In addition, the Dual-Attention Weighted Aggregation (DAWA) module adaptively fuses same-scale features, improving the detection of pests with diverse morphological characteristics. Experimental results from three repeated training runs (random seeds: 42, 2026, 3407) on the IPMaize dataset demonstrate that the proposed method achieves an averaged [email protected] of 78.77% (79.7% with seed = 42) and averaged [email protected]:0.95 of 52.63%. Cross-dataset evaluations on the Tomato Pest&Diseases and IP102 datasets further confirm the model’s strong generalization capability.
SN - 1932-6203
ER -