{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T15:55:06Z","timestamp":1785772506724,"version":"3.56.0"},"reference-count":64,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Effective weed management is essential for reducing yield losses in sugar beet cultivation. However, existing deep learning-based detectors often experience performance degradation in complex field environments characterized by variable illumination, severe occlusion, dense vegetation, and background interference. In addition, models lacking lightweight designs generally require substantial computational resources, leading to increased inference latency and deployment costs that limit their application in real-time agricultural systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address these challenges, we developed CSAG-DETR, a lightweight and robust weed detection framework based on RT-DETR-R18 for accurate weed detection in sugar beet fields. The proposed framework incorporates a Cross-Stage Multi-Scale Network (CSMN) to enhance hierarchical feature interaction, a Cross-Stage Local-Detail Module (CSLM) to preserve fine-grained textures and object boundaries, and Global Attention-Gated Dual-Path Upsampling and Downsampling modules (GAGDU and GAGDD) to improve the stability of cross-scale feature transformation. Furthermore, we constructed the BeetWeed dataset containing nine common weed species and applied diverse data augmentation strategies to improve model robustness under variable field conditions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental results showed that CSAG-DETR achieved an mAP@0.5 of 98.9%, an mAP@0.5:0.95 of 78.6%, and an inference speed of 167.3 FPS on the BeetWeed dataset, outperforming 13 mainstream object detection models in terms of overall detection performance and computational efficiency. Generalization experiments conducted on the public CottonWeedDet12 dataset further demonstrated the strong cross-dataset generalization capability and competitive overall performance of the proposed model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results indicate that CSAG-DETR effectively balances detection accuracy, inference efficiency, and robustness in complex agricultural environments. The proposed framework therefore provides a practical solution for real-time weed detection and may support the deployment of intelligent weed management systems in sugar beet production.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1875124","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T15:14:36Z","timestamp":1785770076000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CSAG-DETR: a lightweight detector for accurate weed detection in sugar beet fields under complex field conditions"],"prefix":"10.3389","volume":"17","author":[{"given":"Xucong","family":"Luo","sequence":"first","affiliation":[{"name":"Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University","place":["Urumqi, China"]},{"name":"Key Laboratory of Software Engineering, Xinjiang University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yisa","family":"Watbek","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University","place":["Urumqi, China"]},{"name":"School of Information Engineering, Changji University","place":["Changji, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyi","family":"Lv","sequence":"additional","affiliation":[{"name":"Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University","place":["Urumqi, China"]},{"name":"Key Laboratory of Software Engineering, Xinjiang University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University","place":["Urumqi, China"]},{"name":"Key Laboratory of Software Engineering, Xinjiang University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reyim","family":"Mamut","sequence":"additional","affiliation":[{"name":"College of Life Sciences and Technology, Xinjiang University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guldiyar","family":"Adil","sequence":"additional","affiliation":[{"name":"College of Life Sciences and Technology, Xinjiang University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yurong","family":"Qian","sequence":"additional","affiliation":[{"name":"Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University","place":["Urumqi, China"]},{"name":"Key Laboratory of Software Engineering, Xinjiang University","place":["Urumqi, China"]},{"name":"School of Computer Science and Technology, Xinjiang University","place":["Urumqi, China"]},{"name":"International Joint Laboratory of Multilingual Cognitive Computing Along the Silk Road","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.13031\/aim.202400564","article-title":"A machine learning extension built on ArcGIS for the detection of weeds in cornfields","author":"Bazrafkan","year":"2024"},{"key":"B2","first-page":"1971","article-title":"Gcnet: Non-local networks meet squeeze-excitation networks and beyond","author":"Cao","year":"2019"},{"key":"B3","doi-asserted-by":"publisher","first-page":"107984","DOI":"10.52202\/079017-3429","article-title":"YOLOv10: Real-time end-to-end object detection","volume":"37","author":"Chen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B4","first-page":"12021","article-title":"Run, don\u2019t walk: Chasing higher flops for faster neural networks","author":"Chen","year":"2023"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1564678","article-title":"Interdisciplinary approaches to image processing for medical robotics","volume":"12","author":"Chen","year":"2025","journal-title":"Front. Med."},{"key":"B6","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-249","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","volume":"11211","author":"Chen","year":"2018"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.05587","article-title":"Rethinking atrous convolution for semantic image segmentation. arxiv 2017","volume":"2","author":"Chen","year":"2019","journal-title":"arXiv. Preprint. arXiv:1706.05587."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109533","article-title":"Weed identification in soybean seedling stage based on UAV images and Faster R-CNN","volume":"227","author":"Cui","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B9","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1038\/s41746-025-01959-7","article-title":"An artificial intelligence cloud platform for OCT-based retinal anomalies screening system in real clinical environments","volume":"8","author":"Chen","year":"2025","journal-title":"NPJ Dig. Med."},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112311","article-title":"A novel object detection model for sugar beet Cercospora leaf spot in field scenarios based on large kernel decomposition and spatial channel interaction attention","volume":"162","author":"Dong","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B11","first-page":"5641","article-title":"RMT: Retentive networks meet vision transformers","author":"Fan","year":"2024"},{"key":"B12","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/tpami.2019.2938758","article-title":"ReS2Net: A new multi-scale backbone architecture","volume":"43","author":"Gao","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.08430","article-title":"Yolox: Exceeding yolo series in 2021","author":"Ge","year":"2021","journal-title":"arXiv. Preprint. arXiv:2107.08430"},{"key":"B14","doi-asserted-by":"publisher","first-page":"29279","DOI":"10.1038\/s41598-025-15275-3","article-title":"Automated weed and crop recognition and classification model using deep transfer learning with optimization algorithm","volume":"15","author":"Gopalakrishnan","year":"2025","journal-title":"Sci. Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1038\/s41698-025-01056-8","article-title":"Integrating genomic and pathological characteristics to enhance prognostic precision in advanced NSCLC","volume":"9","author":"Han","year":"2025","journal-title":"NPJ Precis. Oncol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/tpami.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"He","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B17","doi-asserted-by":"publisher","first-page":"14032","DOI":"10.1038\/s41598-025-96314-x","article-title":"Research on object detection and recognition in remote sensing images based on YOLOv11","volume":"15","author":"He","year":"2025","journal-title":"Sci. Rep."},{"key":"B18","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/tpami.2019.2913372","article-title":"Squeeze-and-excitation networks","volume":"42","author":"Hu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.20787","article-title":"Real-time object detection meets dinov3","author":"Huang","year":"2025","journal-title":"arXiv. Preprint. arXiv:2509.20787"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1556275","article-title":"PHRF-RTDETR: A lightweight weed detection method for upland rice based on RT-DETR","volume":"16","author":"Jin","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7347926","article-title":"ultralytics\/yolov5: v7.0-yolov5 sota realtime instance segmentation","author":"Jocher","year":"2022","journal-title":"Zenodo"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1506524","article-title":"PD-YOLO: A novel weed detection method based on multi-scale feature fusion","volume":"16","author":"Li","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1396568","article-title":"Performance evaluation of semi-supervised learning frameworks for multi-class weed detection","volume":"15","author":"Li","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B24","doi-asserted-by":"publisher","first-page":"16843","DOI":"10.1109\/iccv51070.2023.01549","article-title":"Rethinking vision transformers for MobileNet size and speed","author":"Li","year":"2023","journal-title":"Proc. IEEE\/CVF. Int. Conf. Comput. Vision"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108121","article-title":"Spatial convolutional self-attentionbased transformer module for strawberry disease identification under complex background","volume":"212","author":"Li","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1491706","article-title":"SGSNet: A lightweight deep learning model for strawberry growth stage detection","volume":"15","author":"Li","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B27","doi-asserted-by":"publisher","first-page":"26430","DOI":"10.1038\/s41598-024-77865-x","article-title":"DC-YOLO: An improved field plant detection algorithm based on YOLOv7tiny","volume":"14","author":"Li","year":"2024","journal-title":"Sci. Rep."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1434163","article-title":"Discrimination of leaf diseases in Maize\/Soybean intercropping system based on hyperspectral imaging","volume":"15","author":"Liu","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B29","first-page":"14420","article-title":"EfficientViT: Memory efficient vision transformer with cascaded group attention","author":"Liu","year":"2023"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3390\/s24134379","article-title":"YOLOV8 model for weed detection in wheat fields based on a visual converter and multi-scale feature fusion","volume":"24","author":"Liu","year":"2024","journal-title":"Sensors"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3390\/vetsci12090906","article-title":"A novel lightweight dairy cattle body condition scoring model for edge devices based on tail features and attention mechanisms","volume":"12","author":"Liu","year":"2025","journal-title":"Vet. Sci."},{"key":"B32","doi-asserted-by":"publisher","first-page":"25841","DOI":"10.1038\/s41598-025-09641-4","article-title":"Research on lightweight tunnel cable fire recognition algorithm based on multi-scale features","volume":"15","author":"Liu","year":"2025","journal-title":"Sci. Rep."},{"key":"B33","doi-asserted-by":"publisher","first-page":"2636","DOI":"10.1038\/s41467-024-46954-w","article-title":"Solar-driven sugar production directly from CO2 via a customizable electrocatalytic\u2013biocatalytic flow system","volume":"15","author":"Liu","year":"2024","journal-title":"Nat. Commun."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110306","article-title":"Star-YOLO: A lightweight and efficient model for weed detection in cotton fields using advanced YOLOv8 improvements","volume":"235","author":"Lu","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B35","first-page":"5694","article-title":"Rewrite the stars","author":"Ma","year":"2024"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1518878","article-title":"A scalable multi-modal learning fruit detection algorithm for dynamic environments","volume":"18","author":"Mao","year":"2025","journal-title":"Front. Neurorob."},{"key":"B37","doi-asserted-by":"publisher","first-page":"11330","DOI":"10.1038\/s41598-025-86357-5","article-title":"Hybrid deep learning model for density and growth rate estimation on weed image dataset","volume":"15","author":"Mishra","year":"2025","journal-title":"Sci. Rep."},{"key":"B38","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1038\/s41598-023-50665-5","article-title":"Artificial intelligence enhanced ophthalmological screening in children: Insights from a cohort study in Lubelskie Voivodeship","volume":"14","author":"Piotr","year":"2024","journal-title":"Sci. Rep."},{"key":"B39","first-page":"78","article-title":"MobileNetV4: Universal Models for the Mobile Ecosystem","author":"Qin","year":"2024"},{"key":"B40","doi-asserted-by":"publisher","first-page":"21873","DOI":"10.1038\/s41598-025-07348-0","article-title":"Complex dark environment-oriented object detection method based on YOLO-AS","volume":"15","author":"Ren","year":"2025","journal-title":"Sci. Rep."},{"key":"B41","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.14486","article-title":"Weedsense: Multi-task learning for weed segmentation, height estimation, and growth stage classification","author":"Sarker","year":"2025"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0332461","article-title":"You\u2019re opening Pandora\u2019s Box\u201d: Public attitudes on AI and robotics in Australian agriculture","volume":"20","author":"Sassano","year":"2025","journal-title":"PloS One"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1186\/s12870-024-05797-9","article-title":"Multi-kernel inception aggregation diffusion network for tomato disease detection","volume":"24","author":"Sun","year":"2024","journal-title":"BMC Plant Biol."},{"key":"B45","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.3390\/insects16010102","article-title":"SP-YOLO: A real-time and efficient multi-scale model for pest detection in sugar beet fields","volume":"16","author":"Tang","year":"2025","journal-title":"Insects"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.12524","article-title":"Yolov12: Attention-centric real-time object detectors","author":"Tian","year":"2025","journal-title":"arXiv. Preprint. arXiv:2502.12524"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.1051348","article-title":"Intelligent image analysis recognizes important orchid viral diseases","volume":"13","author":"Tsai","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B49","first-page":"1","article-title":"YOLOv8: A novel object detection algorithm with enhanced performance and robustness","author":"Varghese","year":"2024"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202300668","article-title":"Current trends of raman spectroscopy in clinic settings: Opportunities and challenges","volume":"11","author":"Wang","year":"2024","journal-title":"Adv. Sci."},{"key":"B51","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/cvprw50498.2020.00203","article-title":"CSPNet: A new backbone that can enhance learning capability of CNN","author":"Wang","year":"2020","journal-title":"Proc. IEEE\/CVF. Conf. Comput. Vision Pattern Recogn. Workshops"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.34133\/plantphenomics.0178","article-title":"The state of the art in root system architecture image analysis using artificial intelligence: A review","volume":"6","author":"Weihs","year":"2024","journal-title":"Plant Phenomics."},{"key":"B53","first-page":"16133","article-title":"ConvNeXt V2: Co-designing and scaling ConvNets with masked autoencoders","author":"Woo","year":"2023"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.3390\/plants12091769","article-title":"Study on the detection method for daylily based on YOLOv5 under complex field environments","volume":"12","author":"Yan","year":"2023","journal-title":"Plants"},{"key":"B55","doi-asserted-by":"publisher","first-page":"5719","DOI":"10.1007\/s00371-024-03748-x","article-title":"Lightweight weed detection using re-parameterized partial convolution and collection-distribution feature fusion","volume":"41","author":"Yan","year":"2024","journal-title":"Visual Comput."},{"key":"B56","first-page":"107","article-title":"Field weed classification based on modified LBP and local sparse representation","author":"Yang","year":"2024"},{"key":"B57","doi-asserted-by":"publisher","first-page":"8106","DOI":"10.1038\/s41598-024-58638-y","article-title":"Oriented feature pyramid network for small and dense wheat heads detection and counting","volume":"14","author":"Yu","year":"2024","journal-title":"Sci. Rep."},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0323446","article-title":"A fast hyperspectral change detection algorithm for agricultural crops based on spatial reconstruction","volume":"20","author":"Yuan","year":"2025","journal-title":"PloS One"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202413975","article-title":"High-fidelity computational microscopy via feature-domain phase retrieval","volume":"12","author":"Zhang","year":"2025","journal-title":"Adv. Sci."},{"key":"B60","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/s11554-025-01709-8","article-title":"SCR-DETR: a real-time lightweight DETR model for weed detection","volume":"22","author":"Zhang","year":"2025","journal-title":"J. Real-Time. Img. Process."},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124771","article-title":"UAV imaging hyperspectral for barnyard identification and spatial distribution in paddy fields","volume":"255","author":"Zhang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"B62","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"},{"key":"B63","first-page":"6230","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017"},{"key":"B64","doi-asserted-by":"publisher","first-page":"33284","DOI":"10.1038\/s41598-025-18993-w","article-title":"A lightweight adaptive image deblurring framework using dynamic convolutional neural networks","volume":"15","author":"Zheng","year":"2025","journal-title":"Sci. Rep."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1875124\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T15:14:37Z","timestamp":1785770077000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1875124\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"references-count":64,"alternative-id":["10.3389\/fpls.2026.1875124"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1875124","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"article-number":"1875124"}}