{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:52:44Z","timestamp":1787316764396,"version":"build-2736575974"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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:p>With the rapid development of precision agriculture, seed germination detection is crucial for crop monitoring and variety selection. Existing fully supervised detection methods rely on large-scale annotated datasets, which are costly and time-intensive to obtain in agricultural scenarios. To tackle this issue, we introduce a knowledge distillation\u2013enhanced semi-supervised germination detection framework (KD-SSGD) that requires no pre-trained teacher and supports end-to-end training. Built on a teacher\u2013student architecture, KD-SSGD introduces a lightweight distilled student branch and three key modules: Weighted Boxes Fusion (WBF) to optimize pseudo-label localization, Feature Distillation Loss (FDL) for deep semantic knowledge transfer, and Branch-Adaptive Weighting (BAW) to stabilize multi-branch training. On the Maize-Germ (MG) open-access dataset, KD-SSGD achieves 47.0% mAP with only 1% labeled data, outperforming Faster R-CNN (35.6%), Mean Teacher (41.9%), Soft Teacher (45.1%), and Dense Teacher (45.0%), and reaches 59.3%, 62.8%, and 65.1% mAP at 2%, 5%, and 10% labeled ratios. On the Three Grain Crop (TGC) open-access dataset, which achieves 73.3%, 75.3%, 75.6%, and 76.1% mAP at 1%, 2%, 5%, and 10% labels, surpassing mainstream semi-supervised methods and demonstrating robust cross-crop generalization. The results indicate that KD-SSGD could generate high-quality pseudo-labels, effectively transfer deep knowledge, and achieve stable high-precision detection under limited supervision, providing an efficient and scalable solution for intelligent agricultural perception.<\/jats:p>","DOI":"10.3389\/fpls.2025.1688792","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T06:29:24Z","timestamp":1765175364000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["KD-SSGD: knowledge distillation-enhanced semi-supervised germination detection"],"prefix":"10.3389","volume":"16","author":[{"given":"Chengcheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiantian","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianchang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronghao","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiyao","family":"Gou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1111\/nph.19575","article-title":"Deciphering temporal growth patterns in maize: integrative modeling of phenotype dynamics and underlying genomic variations","volume":"242","author":"Adak","year":"2024","journal-title":"New Phytol."},{"key":"B2","doi-asserted-by":"crossref","first-page":"5562","DOI":"10.1109\/ICCV.2017.593","article-title":"Soft-nms \u2014 improving object detection with one line of code","volume-title":"2017 IEEE international conference on computer vision (ICCV)","author":"Bodla","year":"2017"},{"key":"B3","first-page":"1483","article-title":"Cascade r-cnn: High quality object detection and instance segmentation","volume-title":"IEEE transactions on pattern analysis and machine intelligence","author":"Cai","year":"2021"},{"key":"B4","first-page":"213","article-title":"End-to-end object detection with transformers","volume-title":"In","author":"Carion","year":"2020"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1341335","article-title":"An rgb image dataset for seed germination prediction and vigor detection - maize","volume":"15","author":"Chen","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.13374","article-title":"Collaboration of teachers for semi-supervised object detection","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2405.13374"},{"key":"B7","first-page":"2312.07006","article-title":"Mixed pseudo labels for semi-supervised object detection","volume-title":"arXiv","author":"Chen","year":"2023"},{"key":"B8","doi-asserted-by":"crossref","first-page":"7482","DOI":"10.1109\/CVPR.2018.00781","article-title":"Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Cipolla","year":"2018"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112534","article-title":"Consistency-based semi-supervised learning for oriented object detection","volume":"304","author":"Fu","year":"2024","journal-title":"Knowledge-Based Syst."},{"key":"B10","doi-asserted-by":"publisher","first-page":"11285","DOI":"10.1109\/TII.2024.3403260","article-title":"S2o-det: A semisupervised oriented object detection network for remote sensing images","volume":"20","author":"Fu","year":"2024","journal-title":"IEEE Trans. Ind. Inf."},{"key":"B11","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1186\/s13007-020-00699-x","article-title":"Accurate machine learning-based germination detection, prediction and quality assessment of three grain crops","volume":"16","author":"Genze","year":"2020","journal-title":"Plant Methods"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture14010124","article-title":"Research on real-time detection of maize seedling navigation line based on improved yolov5s lightweighting technology","volume":"14","author":"Gong","year":"2024","journal-title":"Agriculture"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vision"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.07224","article-title":"Deep cnn ensemble with data augmentation for object detection","author":"Guo","year":"2015","journal-title":"arXiv preprint arXiv:1506.07224"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"NeurIPS 2014 Deep Learning Workshop"},{"key":"B16","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s10462-024-11081-x","article-title":"Transfer learning in agriculture: a review","volume":"58","author":"Hossen","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"B17","first-page":"936","article-title":"Feature pyramid networks for object detection","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","author":"Lin","year":"2017"},{"key":"B18","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"B19","first-page":"740","article-title":"Microsoft coco: Common objects in context","volume-title":"European conference on computer vision (ECCV)","author":"Lin","year":"2014"},{"key":"B20","first-page":"1871","article-title":"End-to-end multi-task learning with attention","author":"Liu","year":"2019"},{"key":"B21","first-page":"2304.11832","article-title":"Function-consistent feature distillation","volume-title":"arXiv","author":"Liu","year":"2023"},{"key":"B22","first-page":"2201.12329","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"arXiv","author":"Liu","year":"2022"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.16128","article-title":"Hybrid knowledge transfer through attention and logit distillation for on-device vision systems in agricultural iot","author":"Mugisha","year":"2025","journal-title":"arXiv preprint arXiv:2504.16128"},{"key":"B24","doi-asserted-by":"publisher","first-page":"22030","DOI":"10.1038\/s41598-021-01712-6","article-title":"Robust seed germination prediction using deep learning and rgb image data","volume":"11","author":"Nehoshtan","year":"2021","journal-title":"Sci. Rep."},{"key":"B25","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1109\/ICPR.2006.479","article-title":"Efficient non-maximum suppression","volume":"3","author":"Neubeck","year":"2006","journal-title":"In 18th Int. Conf. Pattern Recognition (ICPR\u201906). vol."},{"key":"B26","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":"B27","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Advances in neural information processing systems","author":"Sohn","year":"2020"},{"key":"B28","first-page":"2005.04757","article-title":"A simple semi-supervised learning framework for object detection","volume-title":"arXiv","author":"Sohn","year":"2020"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117","article-title":"Weighted boxes fusion: Ensembling boxes from different object detection models","volume":"107","author":"Solovyev","year":"2021","journal-title":"Image Vision Computing"},{"key":"B30","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Advances in neural information processing systems","author":"Tarvainen","year":"2017"},{"key":"B31","first-page":"9627","article-title":"Fcos: Fully convolutional one-stage object detection","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","author":"Tian","year":"2019"},{"key":"B32","article-title":"Semi-supervised object detection for agriculture","volume-title":"Proceedings of the 2nd AAAI workshop on AI for agriculture and food systems","author":"Tseng","year":"2023"},{"key":"B33","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2020.01.085","article-title":"Recent advances in deep learning for object detection","volume":"396","author":"Wu","year":"2020","journal-title":"Neurocomputing"},{"key":"B34","first-page":"3060","article-title":"End-to-end semi-supervised object detection with soft teacher","volume-title":"In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Xu","year":"2021"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.plaphe.2025.100011","article-title":"Integrating uav remote sensing and semi-supervised learning for early-stage maize seedling monitoring and geolocation","volume":"7","author":"Yang","year":"2025","journal-title":"Plant Phenomics"},{"key":"B36","doi-asserted-by":"publisher","first-page":"433","DOI":"10.3390\/a18070433","article-title":"A lightweight and efficient plant disease detection method integrating knowledge distillation and dual-scale weighted convolutions","volume":"18","author":"Yang","year":"2025","journal-title":"Algorithms"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3390\/su17125255","article-title":"Deep learning in multimodal fusion for sustainable plant care: A comprehensive review","volume":"17","author":"Yang","year":"2025","journal-title":"Sustainability (2071-1050)"},{"key":"B38","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/978-3-031-20077-9_3","article-title":"Dense teacher: Dense pseudo-labels for semi-supervised object detection","volume-title":"Computer vision \u2013 ECCV 2022","author":"Zhou","year":"2022"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.109956","article-title":"Perceptive teacher: Semi-supervised small object detection of brassica chinensis seedlings and pest infestations","volume":"229","author":"Zhou","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B40","first-page":"2010.04159","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"arXiv","author":"Zhu","year":"2021"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1688792\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T06:29:28Z","timestamp":1765175368000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1688792\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":40,"alternative-id":["10.3389\/fpls.2025.1688792"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1688792","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,8]]},"article-number":"1688792"}}