{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:10:01Z","timestamp":1789575001821,"version":"build-2803163510"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"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>In precision agriculture, accurate and efficient detection of crop pests and diseases is crucial. However, existing models in complex environments are prone to insufficient spatial perception and attenuation of disease texture features, making it difficult to balance recognition accuracy and lightweighting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address this, this study proposes a lightweight spatial perception enhancement hybrid architecture, SpatioFormer. First, a Pixel-level Detail Retrieval (PDR) mechanism is designed. This mechanism leverages cross-layer dynamic routing to facilitate the fusion of deep semantic features with shallow texture features, significantly enhancing the capability to capture disease features. Second, we design a Spatially Adaptive Modulation Attention (SA-SHMA) mechanism, which utilizes large-kernel depthwise convolution to capture contextual information and combines dynamic modulation maps for fine-grained focusing, efficiently recovering spatial details, and suppressing background noise. Furthermore, this paper introduces a Context-Guided Asymmetric Gated Linear Unit (CGA-GLU), which utilizes an asymmetric design focusing on the gating branch and incorporates contextual information for guidance, enhancing the inter-channel representation capability with minimal computational overhead.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Finally, extensive experiments on the PDDD and Tomato-Village datasets validated the effectiveness of the proposed model. The proposed model achieves a Top-1 accuracy of 81.05% on the PDDD dataset and an\n                      <jats:italic>AP<\/jats:italic>\n                      <jats:sub>50<\/jats:sub>\n                      of 61.53% on the Tomato-Village dataset, with testing latency on edge devices being highly competitive among existing models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Compared to existing lightweight hybrid models, SpatioFormer effectively recovers shallow spatial details and precisely suppresses complex background noise under an extremely low parameter budget. Consequently, it achieves a superior balance between practical disease localization capability and inference latency on resource-constrained edge devices.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1925867","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T15:54:26Z","timestamp":1789574066000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SpatioFormer: spatial perception enhancement for lightweight agricultural pest and disease detection"],"prefix":"10.3389","volume":"17","author":[{"given":"Wenbo","family":"Ma","sequence":"first","affiliation":[{"name":"Shandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and Technology","place":["Weifang, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"Shandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and Technology","place":["Weifang, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and Technology","place":["Weifang, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meichun","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and Technology","place":["Weifang, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Fu","sequence":"additional","affiliation":[{"name":"Shandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and Technology","place":["Weifang, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2024.100500","article-title":"A customised vision transformer for accurate detection and classification of java plum leaf disease","volume":"8","author":"Bhowmik","year":"2024","journal-title":"Smart Agric. Technol."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.109938","article-title":"Artificial neural networks in agriculture, the core of artificial intelligence: What, when, and why","volume":"230","author":"Castillo-Girones","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B3","first-page":"12021","article-title":"Run, don\u2019t walk: chasing higher flops for faster neural networks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2023"},{"key":"B4","doi-asserted-by":"publisher","first-page":"49142","DOI":"10.3233\/IDA-227205","article-title":"Lightweight vision transformer with lite-avpso hyperparameter optimization for agricultural disease recognition","volume":"12","author":"Dai","year":"2025","journal-title":"IEEE Internet Things J"},{"key":"B5","first-page":"3560","article-title":"Attentional feature fusion","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Dai","year":"2021"},{"key":"B6","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"International Conference on Machine Learning","author":"Dauphin","year":"2017"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13007-025-01462-w","article-title":"Development of a unified deep learning approach integrating cnn-based local and vit-based global feature extraction for enhanced cotton disease and pest classification","volume":"21","author":"Dhruw","year":"2025","journal-title":"Plant Methods"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121308","article-title":"Esa-net: An efficient scale-aware network for small crop pest detection","volume":"236","author":"Dong","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.34133\/plantphenomics.0054","article-title":"Pddd-pretrain: a series of commonly used pre-trained models support image-based plant disease diagnosis","volume":"5","author":"Dong","year":"2023","journal-title":"Plant Phenomics"},{"key":"B10","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.compag.2017.03.016","article-title":"Vision-based pest detection based on svm classification method","volume":"137","author":"Ebrahimi","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"B11","doi-asserted-by":"publisher","first-page":"44147","DOI":"10.1109\/ACCESS.2024.3379303","article-title":"Enhanced crop disease detection with efficientnet convolutional group-wise transformer","volume":"12","author":"Feng","year":"2024","journal-title":"IEEE Access"},{"key":"B12","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.inpa.2023.02.007","article-title":"Crop pest image recognition based on the improved vit method","volume":"11","author":"Fu","year":"2024","journal-title":"Inf. Process. Agric."},{"key":"B13","doi-asserted-by":"publisher","first-page":"3305","DOI":"10.1007\/s00530-023-01158-y","article-title":"tomato-village\u201d: a dataset for end-to-end tomato disease detection in a real-world environment","volume":"29","author":"Gehlot","year":"2023","journal-title":"Multimedia Syst."},{"key":"B14","first-page":"4497","article-title":"Mobilemamba: Lightweight multi-receptive visual mamba network","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"He","year":"2025"},{"key":"B15","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/s44196-024-00597-3","article-title":"A multitask learning-based vision transformer for plant disease localization and classification","volume":"17","author":"Hemalatha","year":"2024","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.2101.01169","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM computing surveys (CSUR)"},{"key":"B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/SMARTGENCON56628.2022.10083986","article-title":"Potato leaf disease detection using cnn","volume-title":"2022 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON)","author":"Khobragade","year":"2022"},{"key":"B18","first-page":"14923","article-title":"Efficientvim: Efficient vision mamba with hidden state mixer based state space duality","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Lee","year":"2025"},{"key":"B19","doi-asserted-by":"publisher","first-page":"101401","DOI":"10.1016\/j.jksuci.2022.09.013","article-title":"Slvit: Shuffle-convolution-based lightweight vision transformer for effective diagnosis of sugarcane leaf diseases","volume":"35","author":"Li","year":"2023","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1038\/s43016-024-00994-z","article-title":"Integrating climate\u2013pest interactions into crop projections for sustainable agriculture","volume":"5","author":"Li","year":"2024","journal-title":"Nat. Food"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102210","article-title":"Strawberry r-cnn: Recognition and counting model of strawberry based on improved faster r-cnn","volume":"77","author":"Li","year":"2023","journal-title":"Ecol. Inf."},{"key":"B22","first-page":"2117","article-title":"Feature pyramid networks for object detection","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Lin","year":"2017"},{"key":"B23","first-page":"8759","article-title":"Path aggregation network for instance segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2018"},{"key":"B24","doi-asserted-by":"publisher","first-page":"57480","DOI":"10.48550\/arXiv.2403.19963","article-title":"Efficient modulation for vision networks","volume":"2024","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv:2403.19963"},{"key":"B25","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1007\/s11760-021-02024-y","article-title":"Leaf-based disease detection in bell pepper plant using yolo v5","volume":"16","author":"Mathew","year":"2022","journal-title":"Signal. Image Video Process."},{"key":"B26","doi-asserted-by":"publisher","first-page":"10468","DOI":"10.1038\/s41598-026-41190-2","article-title":"A novel lightweight hybrid cnn\u2013vit for maize leaf disease classification","volume":"16","author":"Mehdipour","year":"2026","journal-title":"Sci. Rep"},{"key":"B27","doi-asserted-by":"publisher","first-page":"29955","DOI":"10.1038\/s41598-025-14847-7","article-title":"Robust multiclass classification of crop leaf diseases using hybrid deep learning and grad-cam interpretability","volume":"15","author":"Murugesan","year":"2025","journal-title":"Sci. Rep."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2025.3604745","article-title":"An energy-efficient high resolution vision transformer processor exploiting token similarity beyond token merging","author":"Oh","year":"2025","journal-title":"IEEE Trans. Very Large Scale Integration (VLSI) Syst"},{"key":"B29","doi-asserted-by":"publisher","first-page":"9002","DOI":"10.1038\/s41598-024-59562-x","article-title":"Multiclass classification of diseased grape leaf identification using deep convolutional neural network (dcnn) classifier","volume":"14","author":"Prasad","year":"2024","journal-title":"Sci. Rep."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eja.2025.127625","article-title":"Early detection of tomato leaf diseases using transformers and transfer learning","volume":"168","author":"Shehu","year":"2025","journal-title":"Eur. J. Agron."},{"key":"B31","first-page":"17773","article-title":"Transnext: Robust foveal visual perception for vision transformers","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Shi","year":"2024"},{"key":"B32","first-page":"5332","article-title":"Few-shot adaptation of grounding dino for agricultural domain","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Singh","year":"2025"},{"key":"B33","doi-asserted-by":"publisher","first-page":"45377","DOI":"10.1109\/ACCESS.2023.3273317","article-title":"A deep features extraction model based on the transfer learning model and vision transformer \u201ctlmvit\u201d for plant disease classification","volume":"11","author":"Tabbakh","year":"2023","journal-title":"IEEE Access"},{"key":"B34","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/s11042-022-13144-z","article-title":"Vgg-icnn: A lightweight cnn model for crop disease identification","volume":"82","author":"Thakur","year":"2023","journal-title":"Multimedia Tools Appl."},{"key":"B35","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s41348-024-01033-6","article-title":"Enconv: enhanced cnn for leaf disease classification","volume":"132","author":"Thanjaivadivel","year":"2025","journal-title":"J. Plant Dis. Prot."},{"key":"B36","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1007\/s43621-024-00307-1","article-title":"Efficient identification and classification of apple leaf diseases using lightweight vision transformer (vit)","volume":"5","author":"Ullah","year":"2024","journal-title":"Discover Sustainability"},{"key":"B37","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B38","first-page":"15909","article-title":"Repvit: Revisiting mobile cnn from vit perspective","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2024"},{"key":"B39","first-page":"9718","article-title":"Lsnet: See large, focus small","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Wang","year":"2025"},{"key":"B40","first-page":"3007","article-title":"Carafe: Content-aware reassembly of features","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang","year":"2019"},{"key":"B41","doi-asserted-by":"publisher","first-page":"4203","DOI":"10.48550\/arXiv.2203.11926","article-title":"Focal modulation networks","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3390\/horticulturae11060671","article-title":"Agrilitenet: lightweight multi-scale tomato pest and disease detection for agricultural robots","volume":"11","author":"Yang","year":"2025","journal-title":"Horticulturae"},{"key":"B43","first-page":"4484","article-title":"Mambaout: Do we really need mamba for vision","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yu","year":"2025"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1109\/TCAD.2024.3490173","article-title":"Hyctor: A hybrid cnn-transformer network accelerator with flexible weight\/output stationary dataflow and multicore extension","volume":"44","author":"Yuan","year":"2024","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"B45","first-page":"5756","article-title":"Shvit: Single-head vision transformer with memory efficient macro design","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yun","year":"2024"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1007\/s00530-022-01034-1","article-title":"Sevit: a large-scale and fine-grained plant disease classification model based on transformer and attention convolution","volume":"29","author":"Zeng","year":"2023","journal-title":"Multimedia Syst."},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1016\/j.scienta.2026.114855","article-title":"Dtbi-yolov8-seg: A dual-backbone deep learning framework for automated tomato ripeness detection in greenhouse environments","volume":"361","author":"Zhao","year":"2026","journal-title":"Sci. Hortic."},{"key":"B48","doi-asserted-by":"publisher","first-page":"22947","DOI":"10.48550\/arXiv.2501.15369","article-title":"iformer: Integrating convnet and transformer for mobile application","volume":"2025","author":"Zheng","year":"2025","journal-title":"arXiv preprint arXiv:2501.15369"},{"key":"B49","first-page":"20135","article-title":"Care transformer: Mobile-friendly linear visual transformer via decoupled dual interaction","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Zhou","year":"2025"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1925867\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T15:54:31Z","timestamp":1789574071000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1925867\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":49,"alternative-id":["10.3389\/fpls.2026.1925867"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1925867","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1925867"}}