The DOI matches its Crossref record; the references it cites are not checked yet.
AGRI-KD: A lightweight multi-task framework for rice disease diagnosis with localization and severity quantification
Open accessAbstract
Automated rice disease diagnosis has largely been framed as a classification problem, yet a class label alone is insufficient for field decisions: effective disease management depends on knowing where the infection is, how much leaf area it covers, and how severe it has become. Methods that supply this spatial and quantitative information, such as object detectors or segmentation networks, are typically too computationally heavyweight for the entry-level smartphones available to smallholder farmers, while lightweight classifiers omit it entirely. We present AGRI-KD, a single lightweight model that resolves this tension by producing five outputs simultaneously: disease classification, spatial localization, infected area percentage (IAP), severity grade, and lesion count. A three-teacher ensemble (ResNet-50, DenseNet-121, EfficientNet-B0) is distilled into a 6.97 MB MobileNetV3-Small student through multi-teacher knowledge distillation, learned attention supervision that trains localization maps directly rather than relying on post-hoc visualization, and dedicated agricultural prediction heads. On the field-collected RiceLeafDiseaseBD dataset (9,769 images, 21,460 verified bounding boxes, six classes), AGRI-KD preserves baseline classification accuracy (90.55% vs. 90.41%, 𝑝 = 0 . 7 2 4 ) while significantly improving localization Dice from 0.276 to 0.575 ( p < 0.001, Cohen’s 𝑑 = 1 . 4 9 9 ). Furthermore, it delivers robust agricultural quantification, achieving leaf-area IAP estimation (5.91% MAE, 𝑅 2 = 0 . 6 8 9 ), severity grading (75.1% accuracy, F1-macro 0.645), and lesion counting ( 𝑅 2 = 0 . 7 1 3 ). The model runs in 14.8 ms on a budget smartphone without GPU or network access. By integrating classification, trained localization, and agricultural regression in one deployment-validated model, AGRI-KD delivers comprehensive disease diagnosis within the constraints of entry-level mobile hardware.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
The citation lists haven’t been fetched yet
References 32
Research works printed but not linked: 34
- Savary, 2019, The global burden of pathogens and pests on major food crops, Nat. Ecol. Evol., 3, 430, 10.1038/s41559-018-0793-y · DOI · Paper page
- Mohanty, 2016, Using deep learning for image-based plant disease detection, Front. Plant Sci., 7, 1419, 10.3389/fpls.2016.01419 · DOI
- Ferentinos, 2018, Deep learning models for plant disease detection and diagnosis, Comput. Electron. Agric., 145, 311, 10.1016/j.compag.2018.01.009 · DOI
- Too, 2019, A comparative study of fine-tuning deep learning models for plant disease identification, Comput. Electron. Agric., 161, 272, 10.1016/j.compag.2018.03.032 · DOI
- Bock, 2010, Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging, Crit. Rev. Plant Sci., 29, 59, 10.1080/07352681003617285 · DOI
- Arnal Barbedo, 2013, Digital image processing techniques for detecting, quantifying and classifying plant diseases, SpringerPlus, 2, 660, 10.1186/2193-1801-2-660 · DOI
- Selvaraju, 2020, Grad-CAM: visual explanations from deep networks via gradient-based localization, Int. J. Comput. Vis., 128, 336, 10.1007/s11263-019-01228-7 · DOI · Paper page
- Zhang, 2018, Top-down neural attention by excitation backprop, Int. J. Comput. Vis., 126, 1084, 10.1007/s11263-017-1059-x · DOI
- Kamilaris, 2018, Deep learning in agriculture: a survey, Comput. Electron. Agric., 147, 70, 10.1016/j.compag.2018.02.016 · DOI
- G. Hinton, O. Vinyals, J. Dean, Distilling the knowledge in a neural network,(2015). arXiv preprint arXiv:1503.02531. · arXiv
- A. Romero, N. Ballas, S.E. Kahou, A. Chassang, C. Gatta, Y. Bengio, FitNets: hints for thin deep nets, 2015. arXiv: 1412.6550 [cs.LG]. · arXiv
- S. Zagoruyko, N. Komodakis, Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer, (2016). arXiv preprint arXiv:1612.03928. · arXiv
- Liu, 2024, Tomato leaf disease recognition based on multi-task distillation learning, Front. Plant Sci., 14, 10.3389/fpls.2023.1330527 · DOI
- Luan, 2026, Accurate and efficient recognition of mixed diseases in apple leaves using a multi-task learning approach, Agriculture, 16, 71, 10.3390/agriculture16010071 · DOI
- Sethy, 2020, Deep feature based rice leaf disease identification using support vector machine, Comput. Electron. Agric., 175, 10.1016/j.compag.2020.105527 · DOI
- Lu, 2017, Identification of rice diseases using deep convolutional neural networks, Neurocomputing, 267, 378, 10.1016/j.neucom.2017.06.023 · DOI
- Chen, 2021, Identification of rice plant diseases using lightweight attention networks, Expert Syst. Appl., 169, 10.1016/j.eswa.2020.114514 · DOI
- Jiang, 2019, Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks, IEEE Access, 7, 59069, 10.1109/ACCESS.2019.2914929 · DOI
- Jiang, 2021, LayerCAM: exploring hierarchical class activation maps for localization, IEEE Trans. Image Process., 30, 5875, 10.1109/TIP.2021.3089943 · DOI
- Ren, 2015, Faster R-CNN: towards real-time object detection with region proposal networks, Adv. Neural Inf. Process. Syst., 28, 91
- Fuentes, 2017, A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition, Sensors, 17, 2022, 10.3390/s17092022 · DOI
- Cap, 2020, LeafGAN: an effective data augmentation method for practical plant disease diagnosis, IEEE Trans. Autom. Sci. Eng., 19, 1258, 10.1109/TASE.2020.3041499 · DOI
- Y. Tian, D. Krishnan, P. Isola, Contrastive representation distillation,(2019). arXiv preprint arXiv:1910.10699. · arXiv
- Huang, 2023, Knowledge distillation facilitates the lightweight and efficient plant diseases detection model, Plant Phenomics, 5, 0062, 10.34133/plantphenomics.0062 · DOI
- Li, 2025, Lightweight plant disease detection with adaptive multi-scale model and relationship-based knowledge distillation, Expert Syst., 42, 10.1111/exsy.70059 · DOI
- Caruana, 1997, Multitask learning, Mach. Learn., 28, 41, 10.1023/A:1007379606734 · DOI · Paper page
- S. Ruder, An overview of multi-task learning in deep neural networks,(2017). arXiv preprint arXiv:1706.05098. · arXiv
- IRRI, 2002, Standard evaluation system for rice: international rice research institute, PO Box, 933, 1099
- Simhadri, 2025, Deep learning for rice leaf disease detection: a systematic literature review on emerging trends, methodologies and techniques, Inf. Process. Agric., 12, 151
- Chen, 2026, YOLO-EHS: a lightweight deep learning framework for xinmei detection and multi-scale integration in orchard, Smart Agric. Technol., 14
- Gao, 2026, LMPF: lightweight multi-scale prediction framework in lettuce agriculture, Smart Agric. Technol., 14
- Wang, 2017, Automatic image-based plant disease severity estimation using deep learning, Comput. Intell. Neurosci., 2017
- Zhang, 2024, Plant pest and disease lightweight identification model by fusing tensor features and knowledge distillation, Front. Plant Sci., 15, 10.3389/fpls.2024.1443815 · DOI
- I. Loshchilov, F. Hutter, Decoupled weight decay regularization, (2017). arXiv preprint arXiv:1711.05101. · arXiv
Metadata
- Authors
- Munna, M. M. H., Kabir, A. H., & Tulona, R. F.
- Affiliations
- East West University (BD)
- North South University (BD)
- Independent University, Bangladesh (BD)
- Corresponding author
- Munna, Mohammad Mehedi Hasan
- Venue
- Smart Agricultural Technology
- Publisher
- Elsevier BV
- Published
- 2026-12
- Volume
- 15
- Pages
- 102550
- ISSN
- 2772-3755 (ISSN-L)
- OpenAlex
- W7212375892
- Cited by
- 0
- References
- 32
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Smart Agricultural Technology (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Environmental Science › Ecology › Remote Sensing in Agriculture
- Keywords
- knowledge distillation, MobileNetV3-Small, lesion localization, disease severity classification, lesion counting, smartphone deployment, smallholder farmers
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
