{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:53:46Z","timestamp":1792086826906,"version":"4.4.0"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003851","name":"Department of Education, Heilongjiang Province","doi-asserted-by":"publisher","award":["145509341"],"award-info":[{"award-number":["145509341"]}],"id":[{"id":"10.13039\/501100003851","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009996","name":"Shaanxi Province Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025BSHSDZZ305"],"award-info":[{"award-number":["2025BSHSDZZ305"]}],"id":[{"id":"10.13039\/501100009996","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Crop diseases threaten agricultural productivity, creating a need for recognition models that combine accuracy, robustness, and computational efficiency. Existing CNN-, Transformer-, and state-space-based approaches can weaken fine-grained lesion edges and textures when emphasizing global context. We therefore propose MambaSeed, a lightweight hybrid network built on MambaVisionMixer and equipped with the Local Continuous Branch Injection mechanism, hereafter LCBI. This mechanism repeatedly introduces local feature compensation during hierarchical modeling, preserving high-frequency cues while maintaining global dependency modeling. On the Tomato, Corn, and Potato datasets, MambaSeed achieved accuracies of 98.97%, 98.06%, and 95.87%, respectively, with 1.13M parameters and 0.240G MACs. In the batch-one FP32 GPU benchmark, its latency was 3.39 ms\/image on an NVIDIA RTX 4090. Without a hardware accelerator, the median CPU latency was 25.35 ms\/image with one thread and 15.61 ms\/image with four threads. Ablation, cross-architecture frequency analysis, and controlled perturbation tests further showed that LCBI strengthens high-frequency feature retention and maintains stable recognition under visual degradation. Together, these results show that MambaSeed provides a compact balance of accuracy, efficiency, and robustness across both accelerator-based and CPU-only inference settings.<\/jats:p>","DOI":"10.1371\/journal.pone.0359350","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:41:03Z","timestamp":1792086063000},"page":"e0359350","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["MambaSeed: A lightweight Mamba-based hybrid vision network for tomato leaf disease recognition"],"prefix":"10.1371","volume":"21","author":[{"given":"XueShen","family":"Wang","sequence":"first","affiliation":[{"name":"Qiqihar University","place":["Qiqihar, Heilongjiang, China"],"department":["College of Computer and Control Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qiqihar University","place":["Qiqihar, Heilongjiang, China"],"department":["College of Computer and Control Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yayong","family":"Chen","sequence":"additional","affiliation":[{"name":"Xi\u2019an University of Technology","place":["Xi\u2019an, China"],"department":["State Key Laboratory of Water Engineering Ecology and Environment in Arid Area"]},{"name":"Xi\u2019an University of Technology","place":["Xi\u2019an, China"],"department":["School of Water Resources and Hydro-electric Engineering of XUT"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YunLong","family":"Li","sequence":"additional","affiliation":[{"name":"Qiqihar University","place":["Qiqihar, Heilongjiang, China"],"department":["College of Computer and Control Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YuJie","family":"Qin","sequence":"additional","affiliation":[{"name":"Qiqihar University","place":["Qiqihar, Heilongjiang, China"],"department":["College of Computer and Control Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ZhongYu","family":"Lv","sequence":"additional","affiliation":[{"name":"Qiqihar University","place":["Qiqihar, Heilongjiang, China"],"department":["College of Computer and Control Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8911-3399","authenticated-orcid":true,"given":"XiangJuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Qiqihar University","place":["Qiqihar, Heilongjiang, China"],"department":["College of Computer and Control Engineering"]},{"name":"Qiqihar University","place":["Qiqihar, Heilongjiang, China"],"department":["Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"issue":"13","key":"pone.0359350.ref001","first-page":"2559","article-title":"High-Precision Tomato Disease Detection Using NanoSegmenter Based on Transformer and Lightweighting","volume":"12","author":"Y Liu","year":"2023","journal-title":"Plants (Basel)"},{"key":"pone.0359350.ref002","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.compag.2018.11.005","article-title":"Automated leaf disease detection in different crop species through image features analysis and one class classifiers","volume":"156","author":"XE Pantazi","year":"2019","journal-title":"Comput Electron Agric"},{"key":"pone.0359350.ref003","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.3390\/agronomy15051079","article-title":"From convolutional networks to vision transformers: evolution of deep learning in agricultural pest and disease identification","volume":"15","author":"M Zhang","year":"2025","journal-title":"Agronomy"},{"key":"pone.0359350.ref004","doi-asserted-by":"crossref","first-page":"1409544","DOI":"10.3389\/fpls.2024.1409544","article-title":"Revolutionizing tomato disease detection in complex environments","volume":"15","author":"D Xin","year":"2024","journal-title":"Front Plant Sci"},{"key":"pone.0359350.ref005","doi-asserted-by":"crossref","first-page":"106975","DOI":"10.1016\/j.cropro.2024.106975","article-title":"Identification of tomato leaf diseases based on DGP-SNNet","volume":"187","author":"T Jian","year":"2025","journal-title":"Crop Protection"},{"key":"pone.0359350.ref006","doi-asserted-by":"crossref","first-page":"107181","DOI":"10.1016\/j.cropro.2025.107181","article-title":"Multi-component image analysis for citrus disease detection using convolutional neural networks","volume":"193","author":"P Sharma","year":"2025","journal-title":"Crop Protection"},{"key":"pone.0359350.ref007","doi-asserted-by":"crossref","first-page":"107118","DOI":"10.1016\/j.cropro.2025.107118","article-title":"Tea leaf disease recognition using attention convolutional neural network and handcrafted features","volume":"190","author":"P Wu","year":"2025","journal-title":"Crop Protection"},{"key":"pone.0359350.ref008","doi-asserted-by":"crossref","first-page":"110117","DOI":"10.1016\/j.engappai.2025.110117","article-title":"Resource constraint crop damage classification using depth channel shuffling","volume":"144","author":"MT Islam","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0359350.ref009","doi-asserted-by":"crossref","first-page":"128636","DOI":"10.1016\/j.eswa.2025.128636","article-title":"Channel grouping vision transformer for lightweight fruit and vegetable recognition","volume":"292","author":"C Liu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"pone.0359350.ref010","doi-asserted-by":"crossref","first-page":"127743","DOI":"10.1016\/j.eswa.2025.127743","article-title":"An enhanced vision transformer network for efficient and accurate crop disease detection","volume":"283","author":"MdA Haque","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"pone.0359350.ref011","doi-asserted-by":"crossref","DOI":"10.1007\/s40747-024-01764-x","article-title":"A hybrid Framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer","volume":"11","author":"S Aboelenin","year":"2025","journal-title":"Complex Intell Syst"},{"key":"pone.0359350.ref012","doi-asserted-by":"crossref","first-page":"113177","DOI":"10.1016\/j.patcog.2026.113177","article-title":"ConMamba: Contrastive vision Mamba for plant disease detection","volume":"176","author":"AA Mamun","year":"2026","journal-title":"Pattern Recognition"},{"key":"pone.0359350.ref013","doi-asserted-by":"crossref","first-page":"100730","DOI":"10.1016\/j.atech.2024.100730","article-title":"Smart UAV-assisted rose growth monitoring with improved YOLOv10 and Mamba restoration techniques","volume":"10","author":"F Zhao","year":"2025","journal-title":"Smart Agricultural Technology"},{"key":"pone.0359350.ref014","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1007\/s11119-025-10252-2","article-title":"Smart UAV-assisted blueberry maturity monitoring with Mamba-based computer vision","volume":"26","author":"F Zhao","year":"2025","journal-title":"Precis Agric"},{"key":"pone.0359350.ref015","doi-asserted-by":"crossref","first-page":"129447","DOI":"10.1016\/j.neucom.2025.129447","article-title":"H-vmunet: High-order Vision Mamba UNet for medical image segmentation","volume":"624","author":"R Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"pone.0359350.ref016","doi-asserted-by":"crossref","first-page":"112480","DOI":"10.1016\/j.engappai.2025.112480","article-title":"A mamba-quantum attention transformer-convolutional network for automated pest and disease detection","volume":"162","author":"D Tang","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0359350.ref017","unstructured":"Yu A, Lyu D, Lim SH, Mahoney MW, Erichson NB. Tuning frequency bias of state space models. 2024. doi: 10.48550\/arXiv.2410.02035"},{"key":"pone.0359350.ref018","doi-asserted-by":"crossref","unstructured":"Zhang T, Zhu Y, Zhao J, Cui G, Zheng Y. Exploring state space model in wavelet domain: An infrared and visible image fusion network via wavelet transform and state space model. 2025. http:\/\/dx.doi.org\/10.48550\/arXiv.2503.18378","DOI":"10.1109\/ICME59968.2025.11209539"},{"key":"pone.0359350.ref019","doi-asserted-by":"crossref","first-page":"100480","DOI":"10.1016\/j.atech.2024.100480","article-title":"Feature engineering to identify plant diseases using image processing and artificial intelligence: A comprehensive review","volume":"8","author":"SM Javidan","year":"2024","journal-title":"Smart Agricultural Technology"},{"issue":"10","key":"pone.0359350.ref020","doi-asserted-by":"crossref","first-page":"4769","DOI":"10.3390\/s23104769","article-title":"Plant Disease Detection and Classification: A Systematic Literature Review","volume":"23","author":"Ramanjot","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0359350.ref021","doi-asserted-by":"crossref","first-page":"111952","DOI":"10.1016\/j.compag.2026.111952","article-title":"A self-supervised learning based method for fish disease diagnosis utilizing extremely limited samples","volume":"250","author":"Z Liu","year":"2026","journal-title":"Comput Electron Agric"},{"key":"pone.0359350.ref022","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Kautz J. MambaVision: A hybrid mamba-transformer vision backbone. 2025. doi: 10.48550\/arXiv.2407.08083","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"pone.0359350.ref023","doi-asserted-by":"crossref","first-page":"240","DOI":"10.3390\/agriculture13020240","article-title":"A high-precision detection method of apple leaf diseases using improved faster r-cnn","volume":"13","author":"X Gong","year":"2023","journal-title":"Agriculture"},{"key":"pone.0359350.ref024","doi-asserted-by":"crossref","first-page":"2303","DOI":"10.3390\/agronomy14102303","article-title":"Pest Detection Based on Lightweight Locality-Aware Faster R-CNN","volume":"14","author":"KR Li","year":"2024","journal-title":"Agronomy"},{"issue":"16","key":"pone.0359350.ref025","doi-asserted-by":"crossref","first-page":"2882","DOI":"10.3390\/rs17162882","article-title":"PLCNet: A 3D-CNN-Based Plant-Level Classification Network Hyperspectral Framework for Sweetpotato Virus Disease Detection","volume":"17","author":"Q Zhang","year":"2025","journal-title":"Remote Sensing"},{"issue":"1","key":"pone.0359350.ref026","article-title":"A twin CNN-based framework for optimized rice leaf disease classification with feature fusion","volume":"12","author":"P Pai","year":"2025","journal-title":"J Big Data"},{"key":"pone.0359350.ref027","doi-asserted-by":"crossref","first-page":"115532","DOI":"10.1016\/j.asoc.2026.115532","article-title":"Entropy-informed deep residual network for nonlinear EEG dynamics in fine-grained driver state recognition","volume":"201","author":"J Chen","year":"2026","journal-title":"Applied Soft Computing"},{"key":"pone.0359350.ref028","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1007\/s44196-025-01063-4","article-title":"Spike-TCN with depthwise-separable convolution and attention for efficient time series prediction","volume":"18","author":"Y Dan","year":"2025","journal-title":"Int J Comput Intell Syst"},{"issue":"3","key":"pone.0359350.ref029","doi-asserted-by":"crossref","first-page":"592","DOI":"10.3390\/rs14030592","article-title":"Transformer Neural Network for Weed and Crop Classification of High Resolution UAV Images","volume":"14","author":"R Reedha","year":"2022","journal-title":"Remote Sensing"},{"issue":"6","key":"pone.0359350.ref030","doi-asserted-by":"crossref","first-page":"185","DOI":"10.3390\/agriengineering7060185","article-title":"ViT-RoT: Vision Transformer-Based Robust Framework for Tomato Leaf Disease Recognition","volume":"7","author":"S Nishankar","year":"2025","journal-title":"AgriEngineering"},{"key":"pone.0359350.ref031","doi-asserted-by":"crossref","first-page":"112271","DOI":"10.1016\/j.engappai.2025.112271","article-title":"ImobileTransformer: A fusion-based lightweight model for rice disease identification","volume":"161","author":"Y Lu","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0359350.ref032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2026.3651284","article-title":"A CNN-Transformer Hybrid Network With Boundary Guidance for Mapping Cropland Field Parcels From High-Resolution Remote Sensing Imagery","volume":"64","author":"J Xie","year":"2026","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0359350.ref033","doi-asserted-by":"crossref","first-page":"101160","DOI":"10.1109\/ACCESS.2025.3576990","article-title":"PlantHealthNet: Transformer-Enhanced Hybrid Models for Disease Diagnosis and Severity Estimation in Agriculture","volume":"13","author":"A Iqbal","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0359350.ref034","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1007\/s11119-025-10246-0","article-title":"Assessing the capability of YOLO- and transformer-based object detectors for real-time weed detection","volume":"26","author":"A Allmendinger","year":"2025","journal-title":"Precision Agriculture"},{"key":"pone.0359350.ref035","doi-asserted-by":"crossref","first-page":"3766","DOI":"10.1109\/TIFS.2026.3679936","article-title":"Neural Architecture Search-Based Global\u2013Local Vision Mamba for Palm-Vein Recognition","volume":"21","author":"H Qin","year":"2026","journal-title":"IEEE TransInformForensic Secur"},{"issue":"4","key":"pone.0359350.ref036","doi-asserted-by":"crossref","first-page":"870","DOI":"10.3390\/agronomy15040870","article-title":"YOLO-BSMamba: A YOLOv8s-Based Model for Tomato Leaf Disease Detection in Complex Backgrounds","volume":"15","author":"Z Liu","year":"2025","journal-title":"Agronomy"},{"issue":"12","key":"pone.0359350.ref037","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.3390\/e27121211","article-title":"AdaptPest-Net: A Task-Adaptive Network with Graph-Mamba Fusion for Multi-Scale Agricultural Pest Recognition","volume":"27","author":"J Zou","year":"2025","journal-title":"Entropy (Basel)"},{"issue":"1","key":"pone.0359350.ref038","doi-asserted-by":"crossref","first-page":"10933","DOI":"10.1038\/s41598-024-80977-z","article-title":"Visual Mamba UNet fusion multi-scale attention and detail infusion for unsound corn kernels segmentation","volume":"15","author":"K Zhao","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0359350.ref039","doi-asserted-by":"crossref","first-page":"110676","DOI":"10.1016\/j.bspc.2026.110676","article-title":"Enhancing Unseen Driver State Detection: An EEG-Based Framework with Brain Connectivity and Depthwise Separable Convolutional Neural Networks","volume":"124","author":"J Chen","year":"2026","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0359350.ref040","unstructured":"Hughes DP, Salathe M. An open access repository of images on plant health to enable the development of mobile disease diagnostics. 2016. doi: 10.48550\/arXiv.1511.08060"},{"issue":"2","key":"pone.0359350.ref041","doi-asserted-by":"crossref","DOI":"10.1002\/widm.70099","article-title":"A Review of EEG \u2010Based Driver Fatigue Detection: Nonlinear Dynamics, Brain Networks, and Deep Learning Advances","volume":"16","author":"J Chen","year":"2026","journal-title":"WIREs Data Min & Knowl"},{"issue":"30","key":"pone.0359350.ref042","doi-asserted-by":"crossref","first-page":"306108","DOI":"10.1088\/1361-6501\/ae8d4b","article-title":"Characterizing fatigue-related neural signatures via multi-band EEG features and a three-stage feature optimization strategy for driver fatigue detection","volume":"37","author":"J Chen","year":"2026","journal-title":"Meas Sci Technol"},{"key":"pone.0359350.ref043","doi-asserted-by":"crossref","unstructured":"He H, Zhang J, Cai Y, Chen H, Hu X, Gan Z. Mobilemamba: lightweight multi-receptive visual mamba network. 2024. http:\/\/dx.doi.org\/10.48550\/arXiv.2411.15941","DOI":"10.1109\/CVPR52734.2025.00424"},{"key":"pone.0359350.ref044","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T. An image is worth 16x16 words: Transformers for image recognition at scale. 2021. http:\/\/dx.doi.org\/10.48550\/arXiv.2010.11929"},{"key":"pone.0359350.ref045","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chen B, Wang W, Chen L-C, Tan M, et al. Searching for MobileNetV3. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 2019. 1314\u201324. https:\/\/doi.org\/10.1109\/iccv.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"pone.0359350.ref046","unstructured":"Mehta S, Rastegari M. MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. 2022. http:\/\/dx.doi.org\/10.48550\/arXiv.2110.02178"},{"key":"pone.0359350.ref047","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Ma","year":"2018"},{"issue":"11","key":"pone.0359350.ref048","doi-asserted-by":"crossref","first-page":"10560","DOI":"10.1109\/TPAMI.2025.3596776","article-title":"EMOv2: Pushing 5M Vision Model Frontier","volume":"47","author":"J Zhang","year":"2025","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"pone.0359350.ref049","doi-asserted-by":"crossref","DOI":"10.1007\/s11063-025-11823-0","article-title":"InceptionMamba: A Lightweight and Effective Model for Medical Image Classification Revealing Mamba\u2019s Low-Frequency Bias","volume":"58","author":"B Huang","year":"2026","journal-title":"Neural Process Lett"},{"key":"pone.0359350.ref050","unstructured":"Wang P, Zheng W, Chen T, Wang Z. Anti-oversmoothing in deep vision transformers via the fourier domain analysis: from theory to practice. 2022. http:\/\/dx.doi.org\/10.48550\/arXiv.2203.05962"},{"key":"pone.0359350.ref051","doi-asserted-by":"crossref","unstructured":"Feng M, Ito K, Aoki T, Ohki T, Nishigaki M. Leveraging intermediate features of vision transformer for face anti-spoofing. In: 2025. http:\/\/dx.doi.org\/10.48550\/arXiv.2505.24402","DOI":"10.1109\/CVPRW67362.2025.00331"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:41:12Z","timestamp":1792086072000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359350"}},"subtitle":[],"editor":[{"given":"Marco Antonio","family":"Moreno-Armendariz","sequence":"first","affiliation":[{"name":"Instituto Politecnico Nacional","place":["MEXICO"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,15]]},"references-count":51,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359350","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,15]]}}}