{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T06:24:18Z","timestamp":1786947858064,"version":"build-2736575974"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"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":"\n Introduction<\/jats:title>\n Applying general-purpose vision-language models (VLMs) to crop disease diagnosis presents three critical bottlenecks: reliance on large-scale annotated data, the high computational cost of full finetuning, and existing adaptation methods designed mainly for discriminative classification without sufficient visual-linguistic interaction for generative diagnosis.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We propose BLAP, an adaptive multi-scale visual prompt fine-tuning framework built upon BLIP-2. BLAP introduces an adaptive visual prompt fusion module (APFM) with learnable prompt vectors and a gating mechanism, together with a multi-scale pyramid feature fusion module (PFM). All BLIP-2 backbone parameters are frozen, and only 0.11% of the model parameters are optimized.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n On a few-shot dataset comprising 990 images from 11 crops and 33 disease categories, BLAP achieved 92.78% recognition accuracy, outperforming the BLIP-2+LoRA baseline by 21.67 percentage points. BLEU-4 and ROUGE-L scores reached 0.6507 and 0.7184, respectively, while inference latency increased by only 2.15%.<\/jats:p>\n <\/jats:sec>\n \n Discussion<\/jats:title>\n BLAP provides a lightweight solution that balances accuracy, efficiency, and interpretability for crop disease diagnosis in resource-constrained settings. The proposed dynamic prompt fusion and multiscale pyramid adaptation strategy may also be extended to parameter-efficient fine-tuning of visionlanguage models in other domain-specific applications.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fpls.2026.1901116","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T05:26:03Z","timestamp":1786944363000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["BLAP: lesion-aware adaptive multi-scale visual prompt tuning for few-shot crop disease diagnosis"],"prefix":"10.3389","volume":"17","author":[{"given":"Jiayi","family":"Xiong","sequence":"first","affiliation":[{"name":"College of Agronomy, Sichuan Agricultural University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Libin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Resources and Civil Engineering, Northeastern University","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqing","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Agronomy, Sichuan Agricultural University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dexi","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Plant Protection, Sichuan Academy of Agricultural Sciences","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Agronomy, Sichuan Agricultural University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110052","article-title":"PP-YOLO: Deep learning based detection model to detect apple and cherry trees in orchard based on histogram and wavelet preprocessing techniques","volume":"232","author":"Akdo\u011fan","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B2","unstructured":"AgEval: a benchmark for zero-shot and few-shot plant stress phenotyping with multimodal LLMs\n \n \n \n Arshad\n M. A.\n \n \n Jubery\n T. Z.\n \n \n Roy\n T.\n \n \n Nassiri\n R.\n \n \n Singh\n A. K.\n \n \n Singh\n A.\n \n \n 10.48550\/arXiv.2407.19617\n arXiv\n \n 2024"},{"key":"B3","doi-asserted-by":"publisher","first-page":"16664","DOI":"10.52202\/068431-1212","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B4","doi-asserted-by":"publisher","first-page":"49250","DOI":"10.52202\/075280-2142","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B5","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.compeleceng.2019.04.011","article-title":"Identification of plant leaf diseases using a nine-layer deep convolutional neural network","volume":"76","author":"Geetharamani","year":"2019","journal-title":"Comput. Electr. Eng."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10121388","article-title":"Identification of plant-leaf diseases using CNN and transfer-learning approach","volume":"10","author":"Hassan","year":"2021","journal-title":"Electronics"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110042","article-title":"Improved two-stage deep learning algorithm and lightweight YOLOv5n for classifying cottonseed damage","volume":"232","author":"He","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B8","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"B9","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110806","article-title":"Evaluating and deploying large vision-language models for fruit quality assessment in smart agriculture systems","volume":"238","author":"Huang","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B11","doi-asserted-by":"publisher","first-page":"40","DOI":"10.12133\/j.smartag.SA202504003","article-title":"Low-rank adaptation method for fine-tuning plant disease recognition models","volume":"8","author":"Huang","year":"2026","journal-title":"Smart Agric."},{"key":"B12","unstructured":"An open access repository of images on plant health to enable the development of mobile disease diagnostics\n \n \n \n Hughes\n D. P.\n \n \n Salath\u00e9\n M.\n \n \n 10.48550\/arXiv.1511.08060\n arXiv\n \n 2015"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2025.101761","article-title":"EBGC-RTDETR: a lightweight model for eggplant disease detection with enhanced RT-DETR architecture","volume":"13","author":"Huo","year":"2026","journal-title":"Smart Agric. Technol."},{"key":"B14","unstructured":"15 crop and 45 disease and healthy dataset\n \n \n \n Jain\n A. K.\n \n \n 10.17632\/8fr7grr73p.1\n Mendeley Data\n \n 2026"},{"key":"B15","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.plaphe.2025.100024","article-title":"PlantCaFo: An efficient few-shot plant disease recognition method based on foundation models","volume":"7","author":"Jiang","year":"2025","journal-title":"Plant Phenomics"},{"key":"B17","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: a survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B18","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1186\/s13007-025-01456-8","article-title":"Visual-language transformer-based tomato leaf disease detection for portable greenhouse monitoring device","volume":"21","author":"Kaur","year":"2025","journal-title":"Plant Methods"},{"key":"B19","unstructured":"Data for: identification of plant leaf diseases using a 9-layer deep convolutional neural network\n \n \n \n Krishna\n G.\n \n \n Gopal\n G.\n \n \n 10.17632\/tywbtsjrjv.1\n Mendeley Data\n \n 2019"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1615873","article-title":"Few-shot crop disease recognition using sequence-weighted ensemble model-agnostic meta-learning","volume":"16","author":"Li","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B21","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"B22","first-page":"4582","article-title":"Prefix-tuning: optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"B23","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110661","article-title":"Transfer large models to crop pest recognition\u2014a cross-modal unified framework for parameters efficient fine-tuning","volume":"237","author":"Liu","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B25","unstructured":"PEFT: state-of-the-art parameter-efficient fine-tuning methods\n \n \n \n Mangrulkar\n S.\n \n \n Gugger\n S.\n \n \n Debut\n L.\n \n \n Belkada\n Y.\n \n \n Paul\n S.\n \n \n Bossan\n B.\n \n \n \n 2022"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2016.01419","article-title":"Using deep learning for image-based plant disease detection","volume":"7","author":"Mohanty","year":"2016","journal-title":"Front. Plant Sci."},{"key":"B27","first-page":"8024","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2023.100307","article-title":"Usage of few-shot learning and meta-learning in agriculture: a literature review","volume":"5","author":"Porto","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.130084","article-title":"A vision-language foundation model for leaf disease identification","volume":"299","author":"Quoc","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"B30","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1038\/s41559-018-0793-y","article-title":"The global burden of pathogens and pests on major food crops","volume":"3","author":"Savary","year":"2019","journal-title":"Nat. Ecol. Evol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"101659","DOI":"10.1016\/j.atech.2025.101659","article-title":"DTM-Unet: A deep learning framework incorporating DenseNet and Transformer for precise identification and quantitative segmentation of cucumber leaf disease","author":"Shi","year":"2025","journal-title":"Smart Agric. Technol."},{"key":"B32","unstructured":"MH-SoyaHealthVision: an Indian UAV and leaf image dataset for integrated crop health assessment\n \n \n \n Shinde\n S.\n \n \n Attar\n V.\n \n \n 10.17632\/hkbgh5s3b7.1\n Mendeley Data\n \n 2024"},{"key":"B33","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017"},{"key":"B34","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1146\/annurev.phyto.43.113004.133839","article-title":"Plant disease: a threat to global food security","volume":"43","author":"Strange","year":"2005","journal-title":"Annu. Rev. Phytopathol."},{"key":"B35","unstructured":"Cucumber disease recognition dataset\n \n \n \n Sultana\n N.\n \n \n Shorif\n S. B.\n \n \n Akter\n M.\n \n \n Uddin\n M. S.\n \n \n 10.17632\/y6d3z6f8z9.1\n Mendeley Data\n \n 2022"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1002\/agj2.21285","article-title":"Few-shot learning for plant disease recognition: a review","volume":"116","author":"Sun","year":"2024","journal-title":"Agron. J."},{"key":"B37","unstructured":"EVA-CLIP: improved training techniques for CLIP at scale\n \n \n \n Sun\n Q.\n \n \n Fang\n Y.\n \n \n Wu\n L.\n \n \n Wang\n X.\n \n \n Cao\n Y.\n \n \n 10.48550\/arXiv.2303.15389\n arXiv\n \n 2023"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.132137","article-title":"SPROUT: symptom-centric prototypical representation optimization and uncertainty-aware tuning for few-shot precision agriculture","volume":"667","author":"Venkatraman","year":"2026","journal-title":"Neurocomputing"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMM.2026.3668670","article-title":"Adaptively fine-tuning and ensembling vision-language model for few-shot image classification","author":"Yan","year":"2026","journal-title":"IEEE Trans. Multimedia"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110442","article-title":"CDIP-ChatGLM3: A dual-model approach integrating computer vision and language modeling for crop disease identification and prescription","volume":"236","author":"Yan","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B41","doi-asserted-by":"publisher","first-page":"195","DOI":"10.11975\/j.issn.1002-6819.202409189","article-title":"Recognizing few-shot crop diseases using multimodal-guided visual Transformer","volume":"41","author":"Yang","year":"2025","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"B42","doi-asserted-by":"publisher","first-page":"50","DOI":"10.3390\/ecrs2023-15833","article-title":"Empirical study of peft techniques for winter-wheat segmentation","volume":"29","author":"Zahweh","year":"2023","journal-title":"Environ. Sci. Proc."},{"key":"B43","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3390\/s24186109","article-title":"Few-shot image classification of crop diseases based on vision-language models","volume":"24","author":"Zhou","year":"2024","journal-title":"Sensors"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1901116\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T05:26:08Z","timestamp":1786944368000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1901116\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":44,"alternative-id":["10.3389\/fpls.2026.1901116"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1901116","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]},"article-number":"1901116"}}