{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T06:15:41Z","timestamp":1788156941323,"version":"build-2803163510"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"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>At the sugar beet seedling stage, crops and weeds look alike, vary widely in scale, and appear against heterogeneous backgrounds, so a detector must judge how reliable each location and scale is, not merely extract multi-scale features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Building on RT-DETR, we propose ASSET-DETR, a relation-aware detector rebuilt at three levels: a sparse-dense attention encoder (ASSET), an attention-gated backbone (CAG-Backbone), and a hypergraph-based neck (HyperFPN). Its Hypergraph-Conditioned Multi-Feature Fusion Module (HC-MFM) conditions the fusion weights on group-level relational semantics, turning multi-scale fusion from aggregation by local statistics into feature arbitration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the public Lincoln Beet benchmark, ASSET-DETR attains 74.2% mAP50 and 51.7% mAP50-95, outperforming twelve representative detectors under a unified protocol, and improves on RT-DETR-R18 by 7.8 and 7.7 percentage points at 21.34 M parameters and 100 FPS. On external datasets, it retains about 56% of its source-domain accuracy, and on OD-SugarBeets, few-shot fine-tuning with a small amount of target-domain annotation restores performance to near source-domain levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>ASSET-DETR is therefore a parameter-efficient candidate for object-level perception in variable-rate spraying and precision weeding, and the results underline the importance of cross-domain degradation and few-shot adaptation for this task.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1931798","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:40:02Z","timestamp":1788154802000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ASSET-DETR: a relation-aware multi-scale feature arbitration network for real-time weed detection in sugar beet fields"],"prefix":"10.3389","volume":"17","author":[{"given":"Haodong","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Gansu Agricultural University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjing","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Gansu Agricultural University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengyu","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Gansu Agricultural University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Gansu Agricultural University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Gansu Agricultural University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Gansu Agricultural University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","article-title":"End-to-end object detection with transformers","volume-title":"Computer Vision \u2013 Eccv 2020","author":"Carion","year":"2020"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1177\/0278364917720510","article-title":"Agricultural robot dataset for plant classification, localization and mapping on sugar beet fields","volume":"36","author":"Chebrolu","year":"2017","journal-title":"Int. J. Robot. Res."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3390\/rs18010169","article-title":"Robust object detection for UAVs in foggy environments with spatial-edge fusion and dynamic task alignment","volume":"18","author":"Dong","year":"2026","journal-title":"Remote Sens."},{"key":"B4","article-title":"An image is worth 16\u00d716 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.1109\/TPAMI.2024.3524377","article-title":"Hyper-YOLO: when visual object detection meets hypergraph computation","volume":"47","author":"Feng","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B6","first-page":"3558","article-title":"Hypergraph neural networks","author":"Feng","year":"2019"},{"key":"B7","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s13007-020-00570-z","article-title":"Deep convolutional neural networks for image-based Convolvulus sepium detection in sugar beet fields","volume":"16","author":"Gao","year":"2020","journal-title":"Plant Methods"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3181","DOI":"10.1109\/TPAMI.2022.3182052","article-title":"HGNN+: general hypergraph neural networks","volume":"45","author":"Gao","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B9","article-title":"SparseFormer: sparse visual recognition via limited latent tokens","author":"Gao","year":"2024"},{"key":"B10","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1111\/wre.12526","article-title":"Advances in site-specific weed management in agriculture\u2014a review","volume":"62","author":"Gerhards","year":"2022","journal-title":"Weed Res."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1226329","article-title":"WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion","volume":"14","author":"Guo","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B12","first-page":"1140","article-title":"SegNeXt: rethinking convolutional attention design for semantic segmentation","author":"Guo","year":"2022"},{"key":"B11","doi-asserted-by":"publisher","first-page":"7178","DOI":"10.1038\/s41598-023-34277-7","article-title":"MSE-FPN: multi-scale semantic enhanced feature pyramid network for object detection","volume":"13","author":"Guo","year":"2023","journal-title":"Sci. Rep."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2026.123840","article-title":"Dual-modal consistency learning for weakly supervised RGB-D camouflaged object detection with scribble annotations","volume":"756","author":"Han","year":"2026","journal-title":"Inf. Sci."},{"key":"B15","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1007\/s00530-025-01993-1","article-title":"WS-RTDT: a wavelet convolution and sparse cubic attention enhanced RT-DETR for crop weed detection","volume":"31","author":"He","year":"2025","journal-title":"Multimed. Syst."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11119-023-10073-1","article-title":"Deep learning techniques for in-crop weed recognition in large-scale grain production systems: a review","volume":"25","author":"Hu","year":"2024","journal-title":"Precis. Agric."},{"key":"B17","first-page":"9099","article-title":"Transformer quality in linear time","author":"Hua","year":"2022"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1556275","article-title":"PHRF-RTDETR: a real-time rice field weed detection method based on improved RT-DETR","volume":"16","author":"Jin","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"191","DOI":"10.25165\/j.ijabe.20201301.4920","article-title":"Crop and weed discrimination using Laws\u2019 texture masks","volume":"13","author":"Kamath","year":"2020","journal-title":"Int. J. Agric. Biol. Eng."},{"key":"B21","first-page":"250","article-title":"High-precision mixed feature fusion network using hypergraph computation for cervical abnormal cell detection","author":"Li","year":"2026"},{"key":"B20","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s44443-026-00595-9","article-title":"HyperDet: a hypergraph-based cross-modal object detection method for UAV imagery","volume":"38","author":"Li","year":"2026","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"B22","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"B23","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"B24","first-page":"21","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016"},{"key":"B25","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"B26","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B28","article-title":"Sparse DETR: efficient end-to-end object detection with learnable sparsity","author":"Roh","year":"2022"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.11048","article-title":"Towards practical object detection for weed spraying in precision agriculture","author":"Salazar-Gomez","year":"2021","journal-title":"arXiv"},{"key":"B30","first-page":"17773","article-title":"TransNeXt: robust foveal visual perception for vision transformers","author":"Shi","year":"2024"},{"key":"B31","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"B32","first-page":"568","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"B33","doi-asserted-by":"publisher","first-page":"9583","DOI":"10.1109\/TPAMI.2024.3419548","article-title":"PhenoBench: a large dataset and benchmarks for semantic image interpretation in the agricultural domain","volume":"46","author":"Weyler","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B34","first-page":"22","article-title":"CvT: introducing convolutions to vision transformers","author":"Wu","year":"2021"},{"key":"B35","first-page":"2184","article-title":"AFPN: asymptotic feature pyramid network for object detection","author":"Yang","year":"2023"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3390\/app15094812","article-title":"EMCF-RTDETR: an efficient multi-scale channel-enhanced RT-DETR for weed detection in soybean fields","volume":"15","author":"Yang","year":"2025","journal-title":"Appl. Sci."},{"key":"B37","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2023"},{"key":"B38","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"B39","first-page":"2952","article-title":"Adapt or perish: adaptive sparse transformer with attentive feature refinement for image restoration","author":"Zhou","year":"2024"},{"key":"B40","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1931798\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:40:04Z","timestamp":1788154804000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1931798\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":40,"alternative-id":["10.3389\/fpls.2026.1931798"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1931798","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"article-number":"1931798"}}