{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T18:16:42Z","timestamp":1783621002889,"version":"3.55.0"},"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2017YFE0135700"],"award-info":[{"award-number":["2017YFE0135700"]}]},{"name":"Zhejiang A&F University Research Startup Funds","award":["203402004501"],"award-info":[{"award-number":["203402004501"]}]},{"name":"Bulgarian National Roadmap for Scientific Infrastructure","award":["D01-98\/26.06.2025"],"award-info":[{"award-number":["D01-98\/26.06.2025"]}]},{"DOI":"10.13039\/501100001635","name":"University of Limerick","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001635","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Agricultural leaf disease detection is crucial for early intervention and yield protection in precision agriculture. Among representative economic crops, such as apples, leaf lesions are typically small and appear in complex backgrounds, making accurate detection performed on resource-constrained embedded devices challenging. To address this, we propose a lightweight small-object detection models, namely the dynamic Differential Compensation Lightweight-YOLO (DCL-YOLO) model and its pruned version (DCL-YOLO-P), based on YOLO11n. A novel Dual-Aspect Feature Complementary Mapping (DAFCM) module type is embedded in their backbone to recover lost semantic and spatial information, while the original YOLO11n\u2019s neck is replaced by an Efficient Enhanced Cross-Scale Feature Fusion (EE-CSFF) module, which incorporates Gated Differential Convolutional Fusion (GDCF) modules to strengthen cross-scale information flow and small-object representation. Experimental results obtained on the ALDSOD dataset show that, compared with the YOLO11n baseline, DCL-YOLO improves recall from 81.9% to 84.6%, mAP\n                    <jats:sub>50<\/jats:sub>\n                    from 86.8% to 88.4%, and mAP\n                    <jats:sub>50:95<\/jats:sub>\n                    from 47.0% to 47.8%, while also reducing the parameter count from 2.58 M to 1.91 M and Giga Floating-Point Operations (GFLOPs) from 6.3 to 5.5. After applying Layer-Adaptive Magnitude-based Pruning (LAMP), the parameter count and GFLOPs are further reduced to 0.75 M and 2.7, respectively, with mAP\n                    <jats:sub>50<\/jats:sub>\n                    and mAP\n                    <jats:sub>50:95<\/jats:sub>\n                    still exceeding the baseline by 1.2 and 0.5 percentage points, respectively. When deployed on an embedded device, the pruned model achieved 15.2 FPS and 139 msec per image, confirming its applicability in real-time scenarios. Furthermore, cross-domain validation, performed on the Global Wheat Head Detection (GWHD) dataset, indicates the stable generalization capabilities of the proposed models across environmental domain shifts. The DCL-YOLO\u2019s source code is publicly available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/q123-code\/dcl-yolo\" xlink:type=\"simple\">https:\/\/github.com\/q123-code\/dcl-yolo<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0352500","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:31:46Z","timestamp":1783618306000},"page":"e0352500","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight real-time detectors of apple-leaf diseases operating on embedded devices"],"prefix":"10.1371","volume":"21","author":[{"given":"Yujie","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjiu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanlin","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0535-7087","authenticated-orcid":true,"given":"Ivan","family":"Ganchev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"issue":"7","key":"pone.0352500.ref001","doi-asserted-by":"crossref","first-page":"1968","DOI":"10.1016\/S2095-3119(21)63822-4","article-title":"Overexpression of MdMIPS1 enhances drought tolerance and water-use efficiency in apple","volume":"21","author":"L Hu","year":"2022","journal-title":"Journal of Integrative Agriculture"},{"key":"pone.0352500.ref002","doi-asserted-by":"crossref","first-page":"110737","DOI":"10.1016\/j.compag.2025.110737","article-title":"A lightweight method for apple disease segmentation using multimodal transformer and sensor fusion","volume":"237","author":"Y Song","year":"2025","journal-title":"Computers and Electronics in Agriculture"},{"issue":"9","key":"pone.0352500.ref003","doi-asserted-by":"crossref","DOI":"10.1002\/aps3.11390","article-title":"The plant pathology challenge 2020 data set to classify foliar disease of apples","volume":"8","author":"R Thapa","year":"2020","journal-title":"Applications in Plant Sciences"},{"issue":"6","key":"pone.0352500.ref004","doi-asserted-by":"crossref","first-page":"7759","DOI":"10.1007\/s11042-022-11915-2","article-title":"Apple leaf disease recognition method with improved residual network","volume":"81","author":"H Yu","year":"2022","journal-title":"Multimed Tools Appl"},{"key":"pone.0352500.ref005","doi-asserted-by":"crossref","first-page":"109028","DOI":"10.1016\/j.compag.2024.109028","article-title":"MCDCNet: Multi-scale constrained deformable convolution network for apple leaf disease detection","volume":"222","author":"B Liu","year":"2024","journal-title":"Computers and Electronics in Agriculture"},{"key":"pone.0352500.ref006","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Dollar P, Girshick R, He K, Hariharan B, Belongie S. Feature pyramid networks for object detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 936\u201344. https:\/\/doi.org\/10.1109\/cvpr.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"issue":"1","key":"pone.0352500.ref007","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1177\/03611981241258753","article-title":"CTAFFNet: CNN\u2013transformer adaptive feature fusion object detection algorithm for complex traffic scenarios","volume":"2679","author":"X Dong","year":"2024","journal-title":"Transportation Research Record: Journal of the Transportation Research Board"},{"key":"pone.0352500.ref008","doi-asserted-by":"crossref","first-page":"109458","DOI":"10.1016\/j.compag.2024.109458","article-title":"MAE-YOLOv8-based small object detection of green crisp plum in real complex orchard environments","volume":"226","author":"Q Liu","year":"2024","journal-title":"Computers and Electronics in Agriculture"},{"key":"pone.0352500.ref009","doi-asserted-by":"crossref","first-page":"110843","DOI":"10.1016\/j.compag.2025.110843","article-title":"SCORE-DETR: An efficient transformer-based network for small and occluded citrus detection","volume":"238","author":"B Zhang","year":"2025","journal-title":"Computers and Electronics in Agriculture"},{"key":"pone.0352500.ref010","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 779\u201388. https:\/\/doi.org\/10.1109\/cvpr.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"pone.0352500.ref011","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A. YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017. 6517\u201325. https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"pone.0352500.ref012","doi-asserted-by":"crossref","first-page":"128459","DOI":"10.1016\/j.eswa.2025.128459","article-title":"MFEL-YOLO for small object detection in UAV aerial images","volume":"291","author":"T Hou","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"pone.0352500.ref013","doi-asserted-by":"crossref","first-page":"103052","DOI":"10.1016\/j.displa.2025.103052","article-title":"MI-DETR: A small object detection model for mixed scenes","volume":"88","author":"B Peng","year":"2025","journal-title":"Displays"},{"key":"pone.0352500.ref014","doi-asserted-by":"crossref","first-page":"122669","DOI":"10.1016\/j.eswa.2023.122669","article-title":"DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defects","volume":"241","author":"Y Zhang","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"pone.0352500.ref015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2025.3602640","article-title":"Lightweight multiscale feature fusion and multireceptive field feature enhancement for small object detection in the aerial images","volume":"63","author":"G Zhou","year":"2025","journal-title":"IEEE Trans Geosci Remote Sensing"},{"issue":"5","key":"pone.0352500.ref016","article-title":"BGM-YOLO: An accurate and efficient detector for detecting plant disease","volume":"20","author":"C Yu","year":"2025","journal-title":"PLoS One"},{"key":"pone.0352500.ref017","author":"G Jocher","year":"2024"},{"key":"pone.0352500.ref018","doi-asserted-by":"crossref","first-page":"104770","DOI":"10.1016\/j.dsp.2024.104770","article-title":"FSM-YOLO: Apple leaf disease detection network based on adaptive feature capture and spatial context awareness","volume":"155","author":"C Yan","year":"2024","journal-title":"Digital Signal Processing"},{"key":"pone.0352500.ref019","doi-asserted-by":"crossref","first-page":"1204569","DOI":"10.3389\/fpls.2023.1204569","article-title":"ALAD-YOLO: An lightweight and accurate detector for apple leaf diseases","volume":"14","author":"W Xu","year":"2023","journal-title":"Front Plant Sci"},{"issue":"9","key":"pone.0352500.ref020","article-title":"Sugarcane stem node detection with algorithm based on improved YOLO11 channel pruning with small target enhancement","volume":"20","author":"C Wen","year":"2025","journal-title":"PLoS One"},{"key":"pone.0352500.ref021","author":"J Lee","year":"2020"},{"issue":"8","key":"pone.0352500.ref022","doi-asserted-by":"crossref","first-page":"8673","DOI":"10.1609\/aaai.v39i8.32937","article-title":"FBRT-YOLO: Faster and better for real-time aerial image detection","volume":"39","author":"Y Xiao","year":"2025","journal-title":"AAAI"},{"key":"pone.0352500.ref023","doi-asserted-by":"crossref","unstructured":"Liu H, Jia C, Shi F, Cheng X, Chen S. SCSegamba: Lightweight structure-aware vision mamba for crack segmentation in structures. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA, 2025. 29406\u201316.","DOI":"10.1109\/CVPR52734.2025.02738"},{"key":"pone.0352500.ref024","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. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. 16965\u201374. https:\/\/doi.org\/10.1109\/cvpr52733.2024.01605","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"pone.0352500.ref025","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. Advances in Neural Information Processing Systems 37, 2024. 107984\u20138011. https:\/\/doi.org\/10.52202\/079017-3429","DOI":"10.52202\/079017-3429"},{"issue":"11","key":"pone.0352500.ref026","doi-asserted-by":"crossref","first-page":"2784","DOI":"10.3390\/agronomy12112784","article-title":"Efficient identification of apple leaf diseases in the wild using convolutional neural networks","volume":"12","author":"Q Yang","year":"2022","journal-title":"Agronomy"},{"key":"pone.0352500.ref027","year":"2023"},{"key":"pone.0352500.ref028","author":"D Hughes","year":"2015"},{"key":"pone.0352500.ref029","author":"F Jingze","year":"2022"},{"key":"pone.0352500.ref030","doi-asserted-by":"crossref","first-page":"3521852","DOI":"10.34133\/2020\/3521852","article-title":"Global Wheat Head Detection (GWHD) Dataset: A large and diverse dataset of high-resolution RGB-labelled images to develop and benchmark wheat head detection methods","volume":"2020","author":"E David","year":"2020","journal-title":"Plant Phenomics"},{"key":"pone.0352500.ref031","author":"G Jocher","year":"2023"},{"key":"pone.0352500.ref032","author":"G Jocher","year":"2024"},{"key":"pone.0352500.ref033","author":"Y Tian","year":"2025"},{"key":"pone.0352500.ref034","author":"M Lei","year":"2025"},{"key":"pone.0352500.ref035","author":"G Jocher","year":"2026"},{"key":"pone.0352500.ref036","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV. Efficientdet: Scalable and efficient object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 2020. 10778\u201387. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"issue":"3","key":"pone.0352500.ref037","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","article-title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","volume":"21","author":"H Li","year":"2024","journal-title":"Journal of Real-Time Image Processing"},{"key":"pone.0352500.ref038","year":"2024"},{"issue":"4","key":"pone.0352500.ref039","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.1109\/TCYB.2020.3008248","article-title":"Kullback\u2013Leibler divergence metric learning","volume":"52","author":"S Ji","year":"2020","journal-title":"IEEE Transactions on Cybernetics"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:31:55Z","timestamp":1783618315000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352500"}},"subtitle":[],"editor":[{"given":"Raman","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":39,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0352500","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]}}}