{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T10:54:10Z","timestamp":1787741650795,"version":"build-2784847793"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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>Few-shot object detection (FSOD) addresses the challenge of object recognition under limited annotation conditions, offering practical advantages for smart agriculture, where large-scale labeling of diverse fruit cultivars is often infeasible. To handle the visual complexity of orchard environments\u2014such as occlusion, subtle morphological differences, and dense foliage\u2014this study presents a lightweight tri-modal fusion framework. The model initially employs a CLIP-based semantic prompt encoder to extract category-aware cues, which guide the Segment Anything Model (SAM) in producing structure-preserving masks. These masks are then incorporated via a Semantic Fusion Module (SFM): a Mask-Saliency Adapter (MSA) and a Feature Enhancement Recomposer (FER), enabling spatially aligned and semantically enriched feature modulation. An Attention-Aware Weight Estimator (AWE) further optimizes the fusion by adaptively balancing semantic and visual streams using global saliency cues. The final predictions are subsequently generated by a YOLOv12 detection head. Experiments conducted on four fruit detection benchmarks\u2014Cantaloupe.v2, Peach.v3, Watermelon.v2, and Orange.v8\u2014demonstrate that the proposed method consistently surpasses five representative FSOD baselines. Performance improvements include +7.9% AP@0.5 on Cantaloupe.v2, +5.4% Precision on Peach.v3, +7.4% Precision on Watermelon.v2, and +5.9% AP@0.75 on Orange.v8. These results underscore the model\u2019s effectiveness in orchard-specific scenarios and its potential to facilitate cultivar identification, digital recordkeeping, and cost-efficient agricultural monitoring.<\/jats:p>","DOI":"10.3389\/fpls.2025.1696622","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T13:55:10Z","timestamp":1764597310000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["A lightweight tri-modal few-shot detection framework for fruit diversity recognition toward digital orchard archiving"],"prefix":"10.3389","volume":"16","author":[{"given":"Huaqiang","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41592-024-02580-4","article-title":"Segment anything for microscopy","volume":"22","author":"Archit","year":"2025","journal-title":"Nat. Methods"},{"key":"B2","first-page":"213","article-title":"End-to-end object detection with transformers","volume-title":"European conference on computer vision","author":"Carion","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1483824","article-title":"Yolopears: a novel benchmark of yolo object detectors for multi-class pear surface defect detection in quality grading systems","volume":"16","author":"Chen","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B4","doi-asserted-by":"publisher","first-page":"3489","DOI":"10.1109\/TIP.2025.3572762","article-title":"Enhancing environmental robustness in few-shot learning via conditional representation learning","volume":"34","author":"Guo","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"B5","first-page":"28608","article-title":"Few-shot object detection with foundation models","author":"Han","year":"2024"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1522510","article-title":"Few-shot object detection for pest insects via features aggregation and contrastive learning","volume":"16","author":"He","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B7","doi-asserted-by":"publisher","first-page":"5903","DOI":"10.3390\/s23135903","article-title":"Fruit detection and counting in apple orchards based on improved yolov7 and multi-object tracking methods","volume":"23","author":"Hu","year":"2023","journal-title":"Sensors"},{"key":"B8","doi-asserted-by":"publisher","first-page":"918","DOI":"10.3390\/agriculture14060918","article-title":"Detection and instance segmentation of grape clusters in orchard environments using an improved mask r-cnn model","volume":"14","author":"Huang","year":"2024","journal-title":"Agriculture"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.955256","article-title":"Accurate segmentation of green fruit based on optimized mask rcnn application in complex orchard","volume":"13","author":"Jia","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B10","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"B11","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":"B12","doi-asserted-by":"publisher","first-page":"127054","DOI":"10.1016\/j.eswa.2025.127054","article-title":"A review of few-shot fine-grained image classification","volume":"275","author":"Lim","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B13","doi-asserted-by":"publisher","first-page":"149","DOI":"10.3390\/computation13060149","article-title":"Application of ai in date fruit detection\u2014performance analysis of yolo and faster r-cnn models","volume":"13","author":"Lipi\u0144ski","year":"2025","journal-title":"Computation"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2020.601475","article-title":"High-throughput phenotyping of morphological seed and fruit characteristics using x-ray computed tomography","volume":"11","author":"Liu","year":"2020","journal-title":"Front. Plant Sci."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.1084847","article-title":"A comprehensive review on acquisition of phenotypic information of prunoideae fruits: Image technology","volume":"13","author":"Liu","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B16","doi-asserted-by":"publisher","first-page":"785","DOI":"10.3390\/horticulturae11070785","article-title":"High-precision complex orchard passion fruit detection using the phd-yolo model improved from yolov11n","volume":"11","author":"Luo","year":"2025","journal-title":"Horticulturae"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1389961","article-title":"Yolo-cfruit: a robust object detection method for camellia oleifera fruit in complex environments","volume":"15","author":"Luo","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.3390\/agronomy13051419","article-title":"Detection and counting of small target apples under complicated environments by using improved yolov7-tiny","volume":"13","author":"Ma","year":"2023","journal-title":"Agronomy"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2021.684328","article-title":"Intelligent fruit yield estimation for orchards using deep learning based semantic segmentation techniques\u2014a review","volume":"12","author":"Maheswari","year":"2021","journal-title":"Front. Plant Sci."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918","article-title":"Segment anything model for medical image analysis: an experimental study","volume":"89","author":"Mazurowski","year":"2023","journal-title":"Med. Image Anal."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1418383","article-title":"Development of a deep-learning phenotyping tool for analyzing image-based strawberry phenotypes","volume":"15","author":"Ndikumana","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B22","doi-asserted-by":"publisher","first-page":"103540","DOI":"10.1016\/j.jag.2023.103540","article-title":"The segment anything model (sam) for remote sensing applications: From zero to one shot","volume":"124","author":"Osco","year":"2023","journal-title":"Int. J. Appl. Earth Observation Geoinformation"},{"key":"B23","first-page":"8681","article-title":"Defrcn: Decoupled faster r-cnn for few-shot object detection","author":"Qiao","year":"2021"},{"key":"B24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"B25","first-page":"1775","article-title":"Integrated grad-cam: Sensitivity-aware visual explanation of deep convolutional networks via integrated gradient-based scoring","volume-title":"ICASSP 2021\u20132021 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"Sattarzadeh","year":"2021"},{"key":"B26","first-page":"618","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Selvaraju","year":"2017"},{"key":"B27","doi-asserted-by":"publisher","first-page":"682","DOI":"10.3390\/agronomy14040682","article-title":"Detection of orchard apples using improved yolov5s-gbr model","volume":"14","author":"Sun","year":"2024","journal-title":"Agronomy"},{"key":"B28","doi-asserted-by":"publisher","first-page":"460","DOI":"10.3390\/agronomy14030460","article-title":"Strawberry maturity recognition based on improved yolov5","volume":"14","author":"Tao","year":"2024","journal-title":"Agronomy"},{"key":"B29","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"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.06957","article-title":"Frustratingly simple few-shot object detection","author":"Wang","year":"2020","journal-title":"arXiv"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.3390\/plants14111729","article-title":"Eld-yolo: A lightweight framework for detecting occluded mandarin fruits in plant research","volume":"14","author":"Wang","year":"2025","journal-title":"Plants"},{"key":"B32","doi-asserted-by":"publisher","first-page":"102307","DOI":"10.1016\/j.inffus.2024.102307","article-title":"Few-shot object detection: Research advances and challenges","volume":"107","author":"Xin","year":"2024","journal-title":"Inf. Fusion"},{"key":"B33","first-page":"9577","article-title":"Meta r-cnn: Towards general solver for instance-level low-shot learning","author":"Yan","year":"2019"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.3390\/electronics14102087","article-title":"Vl-paw: A vision\u2013language dataset for pear, apple and weed","volume":"14","author":"Yu","year":"2025","journal-title":"Electronics"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.03605","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.3390\/agriculture15111173","article-title":"E-clip: An enhanced clip-based visual language model for fruit detection and recognition","volume":"15","author":"Zhang","year":"2025","journal-title":"Agriculture"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.04159","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv"},{"key":"B38","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s00138-023-01486-z","article-title":"Few-shot object detection via data augmentation and distribution calibration","volume":"35","author":"Zhu","year":"2024","journal-title":"Mach. Vision Appl."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1696622\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T13:55:12Z","timestamp":1764597312000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1696622\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":38,"alternative-id":["10.3389\/fpls.2025.1696622"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1696622","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"article-number":"1696622"}}