{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T19:04:04Z","timestamp":1789499044874,"version":"build-2803163510"},"reference-count":54,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["262102210078"],"award-info":[{"award-number":["262102210078"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>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\u2019s 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 mAP@0.5 of 78.77% (79.7% with seed\u2009=\u200942) and averaged mAP@0.5:0.95 of 52.63%. Cross-dataset evaluations on the Tomato Pest&amp;Diseases and IP102 datasets further confirm the model\u2019s strong generalization capability.<\/jats:p>","DOI":"10.1371\/journal.pone.0357034","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T18:14:02Z","timestamp":1789496042000},"page":"e0357034","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["WSD-YOLO: A lightweight YOLO-based model with enhanced feature representation for maize pest detection"],"prefix":"10.1371","volume":"21","author":[{"given":"Shenming","family":"Qu","sequence":"first","affiliation":[{"name":"Henan University","place":["Kaifeng, China"],"department":["School of Software"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Henan University","place":["Kaifeng, China"],"department":["School of Software"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huazhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Henan University","place":["Kaifeng, China"],"department":["School of Software"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichao","family":"Wu","sequence":"additional","affiliation":[{"name":"Henan University","place":["Kaifeng, China"],"department":["School of Computer and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5245-6695","authenticated-orcid":true,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Henan University","place":["Kaifeng, China"],"department":["School of Software"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"issue":"5","key":"pone.0357034.ref001","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1007\/s12571-022-01288-7","article-title":"Global maize production, consumption and trade: trends and R&D implications","volume":"14","author":"O Erenstein","year":"2022","journal-title":"Food Secur"},{"issue":"1","key":"pone.0357034.ref002","doi-asserted-by":"crossref","first-page":"2637","DOI":"10.1038\/s41467-023-38355-2","article-title":"China can be self-sufficient in maize production by 2030 with optimal crop management","volume":"14","author":"N Luo","year":"2023","journal-title":"Nat Commun"},{"issue":"2","key":"pone.0357034.ref003","article-title":"Sustainable management of fall armyworm, Spodoptera frugiperda (J.E. Smith): challenges and proposed solutions from an African perspective","volume":"70","author":"S Nyamutukwa","year":"2024","journal-title":"Int J Pest Manag"},{"issue":"6405","key":"pone.0357034.ref004","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1126\/science.aat3466","article-title":"Increase in crop losses to insect pests in a warming climate","volume":"361","author":"CA Deutsch","year":"2018","journal-title":"Science"},{"issue":"6","key":"pone.0357034.ref005","first-page":"910","article-title":"Improving rice pest management through RP11: a scientifically annotated dataset for adult insect recognition","volume":"15","author":"B Ding","year":"2025","journal-title":"Life (Basel)"},{"issue":"6","key":"pone.0357034.ref006","doi-asserted-by":"crossref","first-page":"568","DOI":"10.3390\/insects16060568","article-title":"Future range shifts in major maize insect pests suggest their increasing impacts on global maize production","volume":"16","author":"Q Wei","year":"2025","journal-title":"Insects"},{"issue":"4","key":"pone.0357034.ref007","doi-asserted-by":"crossref","first-page":"698","DOI":"10.3390\/rs17040698","article-title":"Advances in deep learning applications for plant disease and pest detection: a review","volume":"17","author":"S Wang","year":"2025","journal-title":"Remote Sens"},{"issue":"3","key":"pone.0357034.ref008","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.3390\/ijerph18031112","article-title":"Agriculture development, pesticide application and its impact on the environment","volume":"18","author":"M Tudi","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"pone.0357034.ref009","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: a survey","volume":"147","author":"A Kamilaris","year":"2018","journal-title":"Comput Electron Agric"},{"issue":"4","key":"pone.0357034.ref010","first-page":"1511","article-title":"Classification of cotton leaf spot disease using support vector machine","volume":"3","author":"SP Patil","year":"2014","journal-title":"Int J Eng Res"},{"key":"pone.0357034.ref011","doi-asserted-by":"crossref","first-page":"105809","DOI":"10.1016\/j.compag.2020.105809","article-title":"Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks","volume":"179","author":"E Ayan","year":"2020","journal-title":"Comput Electron Agric"},{"key":"pone.0357034.ref012","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.biosystemseng.2019.02.002","article-title":"Plant disease identification from individual lesions and spots using deep learning","volume":"180","author":"JG Arnal Barbedo","year":"2019","journal-title":"Biosyst Eng"},{"key":"pone.0357034.ref013","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems. vol. 25; 2012. p. 1097\u2013105. Available from: https:\/\/proceedings.neurips.cc\/paper\/2012\/hash\/c399862d3b9d6b76c8436e924a68c45b-Abstract.html"},{"key":"pone.0357034.ref014","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-3-319-90403-0_6","article-title":"Deep learning for plant diseases: detection and saliency map visualisation.","volume-title":"Human and machine learning: visible, explainable, trustworthy and transparent","author":"M Brahimi","year":"2018"},{"key":"pone.0357034.ref015","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2023. p. 7464\u201375. Available from: https:\/\/doi.org\/10.1109\/CVPR52729.2023.00721","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"pone.0357034.ref016","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 779\u201388. Available from: https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"issue":"4","key":"pone.0357034.ref017","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"J Terven","year":"2023","journal-title":"MAKE"},{"key":"pone.0357034.ref018","unstructured":"Yaseen M. What is YOLOv9: an in-depth exploration of the internal features of the next-generation object detector. arXiv:2409.07813; 2024. Available from: doi: 10.48550\/arXiv.2409.07813"},{"key":"pone.0357034.ref019","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J. YOLOX: exceeding YOLO series in 2021. arXiv:2107.08430; 2021. Available from: doi: 10.48550\/arXiv.2107.08430"},{"key":"pone.0357034.ref020","doi-asserted-by":"crossref","unstructured":"Wang A, Chen H, Liu L, Chen K, Lin Z, Han J, et al. YOLOv10: real-time end-to-end object detection. arXiv:2405.14458; 2024. Available from: doi: 10.48550\/arXiv.2405.14458","DOI":"10.52202\/079017-3429"},{"key":"pone.0357034.ref021","unstructured":"Ultralytics. Ultralytics YOLO11. Software; 2024 [cited 2025 Jan 18]. Available from: https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"pone.0357034.ref022","doi-asserted-by":"crossref","first-page":"106694","DOI":"10.1016\/j.compag.2022.106694","article-title":"Real-time growth stage detection model for high degree of occultation using DenseNet-fused YOLOv4","volume":"193","author":"AM Roy","year":"2022","journal-title":"Comput Electron Agric"},{"issue":"1","key":"pone.0357034.ref023","doi-asserted-by":"crossref","first-page":"1447","DOI":"10.1038\/s41598-021-81216-5","article-title":"Tomato detection based on modified YOLOv3 framework","volume":"11","author":"MO Lawal","year":"2021","journal-title":"Sci Rep"},{"issue":"19","key":"pone.0357034.ref024","first-page":"209","article-title":"Crop pest identification based on spatial pyramid pooling and deep convolution neural network","volume":"35","author":"B Zhang","year":"2019","journal-title":"Trans Chin Soc Agric Eng"},{"key":"pone.0357034.ref025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2019\/7630926","article-title":"Detection of apple lesions in orchards based on deep learning methods of CycleGAN and YOLOV3-dense","volume":"2019","author":"Y Tian","year":"2019","journal-title":"J Sens"},{"key":"pone.0357034.ref026","doi-asserted-by":"crossref","unstructured":"Wu X, Zhan C, Lai YK, Cheng MM, Yang J. IP102: a large-scale benchmark dataset for insect pest recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2019. p. 8779\u201388. Available from: https:\/\/doi.org\/10.1109\/CVPR.2019.00899","DOI":"10.1109\/CVPR.2019.00899"},{"key":"pone.0357034.ref027","doi-asserted-by":"crossref","first-page":"100023","DOI":"10.1016\/j.atech.2021.100023","article-title":"Methods of insect image capture and classification: a systematic literature review","volume":"1","author":"DC Amarathunga","year":"2021","journal-title":"Smart Agric Technol"},{"key":"pone.0357034.ref028","doi-asserted-by":"crossref","first-page":"1133060","DOI":"10.3389\/fpls.2023.1133060","article-title":"Crop pest image classification based on improved densely connected convolutional network","volume":"14","author":"H Peng","year":"2023","journal-title":"Front Plant Sci"},{"key":"pone.0357034.ref029","doi-asserted-by":"crossref","first-page":"1619551","DOI":"10.3389\/fpls.2025.1619551","article-title":"Swin Attention Augmented Residual Network: a fine-grained pest image recognition method","volume":"16","author":"X Wang","year":"2025","journal-title":"Front Plant Sci"},{"issue":"13","key":"pone.0357034.ref030","doi-asserted-by":"crossref","first-page":"5543","DOI":"10.3390\/app14135543","article-title":"Enhanced pest recognition using multi-task deep learning with the discriminative attention multi-network","volume":"14","author":"Z Dong","year":"2024","journal-title":"Appl Sci"},{"issue":"1","key":"pone.0357034.ref031","first-page":"100125","article-title":"Comprehensive performance evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on detecting and counting fruitlet in complex orchard environments","volume":"4","author":"R Sapkota","year":"2026","journal-title":"Agric Commun"},{"key":"pone.0357034.ref032","unstructured":"Khanam R, Hussain M. YOLOv11: an overview of the key architectural enhancements. arXiv:2410.17725; 2024. Available from: doi: 10.48550\/arXiv.2410.17725"},{"key":"pone.0357034.ref033","unstructured":"Wang K, Liu J, Cai X. C2PSA-enhanced YOLOv11 architecture: a novel approach for small target detection in cotton disease diagnosis. arXiv:2508.12219; 2025. Available from: doi: 10.48550\/arXiv.2508.12219"},{"key":"pone.0357034.ref034","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie SJ. Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017. p. 936\u201344. Available from: https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"pone.0357034.ref035","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J. Path aggregation network for instance segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2018. p. 8759\u201368. Available from: http:\/\/doi.org\/10.1109\/cvpr.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"issue":"6","key":"pone.0357034.ref036","doi-asserted-by":"crossref","first-page":"3985","DOI":"10.1007\/s10586-022-03802-0","article-title":"Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3","volume":"26","author":"N Khasawneh","year":"2022","journal-title":"Clust Comput"},{"issue":"9","key":"pone.0357034.ref037","doi-asserted-by":"crossref","first-page":"320","DOI":"10.3390\/jimaging11090320","article-title":"YOLO-DCRCF: an algorithm for detecting the wearing of safety helmets and gloves in power grid operation environments","volume":"11","author":"J Zhao","year":"2025","journal-title":"J Imaging"},{"issue":"9","key":"pone.0357034.ref038","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object detection with discriminatively trained part-based models","volume":"32","author":"PF Felzenszwalb","year":"2010","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0357034.ref039","doi-asserted-by":"crossref","unstructured":"Ding X, Guo Y, Ding G, Han J. ACNet: strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks. Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2019. p. 1911\u201320. Available from: https:\/\/doi.org\/10.1109\/ICCV.2019.00200","DOI":"10.1109\/ICCV.2019.00200"},{"key":"pone.0357034.ref040","doi-asserted-by":"crossref","unstructured":"Finder SE, Amoyal R, Treister E, Freifeld O. Wavelet convolutions for large receptive fields. Computer Vision \u2013 ECCV 2024. vol. 15112. Springer; 2024. p. 363\u201380. Available from: https:\/\/doi.org\/10.1007\/978-3-031-72949-2_21","DOI":"10.1007\/978-3-031-72949-2_21"},{"key":"pone.0357034.ref041","first-page":"121352","article-title":"Large separable kernel attention: rethinking the large kernel attention design in CNN","volume":"236","author":"KW Lau","year":"2023","journal-title":"Expert Syst Appl"},{"key":"pone.0357034.ref042","doi-asserted-by":"crossref","unstructured":"Yin D, Hu L, Li B, Zhang Y, Yang X. 5%>100%: breaking performance shackles of full fine-tuning on visual recognition tasks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2025. p. 20071\u201381. Available from: https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/html\/Yin_5100_Breaking_Performance_Shackles_of_Full_Fine-Tuning_on_Visual_Recognition_CVPR_2025_paper.html","DOI":"10.1109\/CVPR52734.2025.01869"},{"key":"pone.0357034.ref043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2024.3370299","article-title":"Hybrid convolutional and attention network for hyperspectral image denoising","volume":"21","author":"S Hu","year":"2024","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"pone.0357034.ref044","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1109\/TIP.2024.3354108","article-title":"DEA-Net: single image dehazing based on detail-enhanced convolution and content-guided attention","volume":"33","author":"Z Chen","year":"2024","journal-title":"IEEE Trans Image Process"},{"issue":"7","key":"pone.0357034.ref045","doi-asserted-by":"crossref","first-page":"446","DOI":"10.3390\/drones7070446","article-title":"TGC-YOLOv5: an enhanced YOLOv5 drone detection model based on transformer, GAM & CA attention mechanism","volume":"7","author":"Y Zhao","year":"2023","journal-title":"Drones"},{"key":"pone.0357034.ref046","unstructured":"Ultralytics. Ultralytics YOLOv8. Software; 2023 [cited 2025 Jan 18]. Available from: https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"pone.0357034.ref047","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q, et al. DETRs beat YOLOs on real-time object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2024. p. 16965\u201374. Available from: https:\/\/doi.org\/10.1109\/CVPR52733.2024.01605","DOI":"10.1109\/CVPR52733.2024.01605"},{"issue":"4","key":"pone.0357034.ref048","doi-asserted-by":"crossref","first-page":"2388","DOI":"10.1109\/TPAMI.2024.3524377","article-title":"Hyper-YOLO: when visual object detection meets hypergraph computation","volume":"47","author":"Y Feng","year":"2025","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"pone.0357034.ref049","doi-asserted-by":"crossref","first-page":"278","DOI":"10.3390\/insects14030278","article-title":"Maize-YOLO: a new high-precision and real-time method for maize pest detection","volume":"14","author":"S Yang","year":"2023","journal-title":"Insects"},{"key":"pone.0357034.ref050","doi-asserted-by":"crossref","unstructured":"Wang CY, Yeh IH, Liao HYM. YOLOv9: learning what you want to learn using programmable gradient information. Computer Vision \u2013 ECCV 2024. vol. 15089. Springer; 2024. p. 1\u201321. Available from: https:\/\/doi.org\/10.1007\/978-3-031-72751-1_1","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"pone.0357034.ref051","unstructured":"Lyu C, Zhang W, Huang H, Zhou Y, Wang Y, Liu Y, et al. RTMDet: an empirical study of designing real-time object detectors. arXiv:2212.07784; 2022. Available from: doi: 10.48550\/arXiv.2212.07784"},{"key":"pone.0357034.ref052","unstructured":"Xu S, Wang X, Lv W, Chang Q, Cui C, Deng K, et al. PP-YOLOE: an evolved version of YOLO. arXiv:2203.16250; 2022. Available from: doi: 10.48550\/arXiv.2203.16250"},{"key":"pone.0357034.ref053","unstructured":"Peng Y, Li H, Wu P, Zhang Y, Sun X, Wu F. D-FINE: redefine regression task of DETRs as fine-grained distribution refinement. International Conference on Learning Representations; 2025. Available from: https:\/\/openreview.net\/forum?id=MFZjrTFE7h"},{"key":"pone.0357034.ref054","unstructured":"Absolute. Tomato pest & diseases dataset. Roboflow Universe; 2023 [cited 2025 Jan 18]. Available from: https:\/\/universe.roboflow.com\/absolute\/tomato-pest-diseases"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T18:14:18Z","timestamp":1789496058000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357034"}},"subtitle":[],"editor":[{"given":"Jia-Lang","family":"Xu","sequence":"first","affiliation":[{"name":"National Taichung University of Science and Technology","place":["TAIWAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":54,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0357034","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]}}}