Deployable Deep Learning for Cross-Domain Plant Leaf Disease Detection via Ensemble Learning, Knowledge Distillation, and Quantization
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Accurate leaf disease detection via smartphone-based deep learning holds immense potential for mitigating global crop losses. However, significant deployment challenges persist when transitioning from controlled laboratory environments to real-world agricultural conditions. Despite recent advances, three fundamental barriers remain: cross-domain generalization, severe class imbalance, and computational limitations for edge deployment. This study introduces the first open cross-domain benchmark for tomato leaf disease detection, unifying PlantVillage and TomatoVillage datasets into 15 harmonized disease classes to enable reproducible evaluation across domains. We propose a unified optimization approach integrating ensemble learning, knowledge distillation, and quantization across 24 deep learning architectures for edge-compatible disease detection. Strategic data augmentation and ADASYN-based balancing mitigate the severe 75:1 class imbalance, while systematic hyperparameter tuning optimizes model configurations. Our four-model ensemble (DenseNet-121, ResNet-101, DenseNet-201, EfficientNet-B4) achieves 99.15% accuracy via soft-voting. Knowledge distillation transfers ensemble capabilities to compact ShuffleNetV2, maintaining 98.53% accuracy with 163× parameter reduction and 43.6× speedup. INT8 quantization provides 671× compression (1.46 MB) while sustaining 97.46% accuracy, enabling 0.29ms inference. Cross-dataset validation demonstrates robust generalization with only 3.45% performance degradation. Grad-CAM++ and LIME-based explainability confirm biologically grounded attention patterns aligned with plant pathology principles. Finally, field deployment via a multilingual and multi-platform Flutter application validates real-world feasibility, establishing the first scalable framework bridging research and practical agricultural deployment. This work sets a standardized benchmark and extensible methodology for future multi-dataset precision agriculture research. Codes and implementations are publicly available at: https://github.com/junayed-hasan/tomato-leaf-ai.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01264-9_8 · Cited by 7,356 · cited 2×
“Mobile-optimized architectures critical for deployment include MobileNetV2 [46] with inverted residual structures, MobileNetV3_Small [47] incorporating neural architecture search optimizations, and ShuffleNetV2 [48] featuring channel shuffle operations.”
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
Chattopadhay, A., Sarkar, A., Howlader, P., & Balasubramanian, V. N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00097 · Cited by 3,639
Popular Ensemble Methods: An Empirical Study
Opitz, D., & Maclin, R. (1999) · Journal of Artificial Intelligence Research · doi:10.1613/jair.614 · Cited by 2,953
Albumentations: fast and flexible image augmentations
Buslaev, A., Iglovikov, V. I., Khvedchenya, E., Parinov, A., Druzhinin, M., & Kalinin, A. A. (2020) · Information · doi:10.3390/info11020125 · Cited by 2,714
Research works printed but not linked: 59
- 2019, The State of Food and Agriculture 2019: Moving Forward on Food Loss and Waste Reduction
- 10.1038/s41598-024-72237-x · DOI
- 10.3389/fpls.2016.01419 · DOI · Paper page
- 10.1038/s41598-025-98015-x · doi:10.1038/s41598-025-98015-x
- 10.1186/s12870-025-06247-w · DOI
- 10.1007/s11042-023-16347-0 · DOI
- 10.1007/s43621-025-01149-1 · doi:10.1007/s43621-025-01149-1
- 10.1016/j.heliyon.2025.e42575 · doi:10.1016/j.heliyon.2025.e42575
- 10.1109/ICEEICT62016.2024.10534539 · doi:10.1109/iceeict62016.2024.10534539
- 10.3389/fpls.2024.1382416 · doi:10.3389/fpls.2024.1382416
- Sun, 2024, Addressing domain shift in deep learning: Challenges and insights from plant disease diagnosis and flower recognition, bioRxiv
- 10.1145/3371158.3371196 · DOI · Paper page
- 10.1109/ACCESS.2023.3263042 · DOI · Paper page
- 10.1007/s00530-023-01158-y · DOI
- 10.1109/ACCESS.2022.3187203 · DOI · Paper page
- 10.1007/s00521-024-09670-6 · DOI
- 10.1080/13682199.2022.2161696 · doi:10.1080/13682199.2022.2161696
- 10.3390/agronomy13030887 · DOI
- 10.3390/agronomy13061455 · DOI
- 10.3390/agronomy14040673 · DOI
- 10.1613/jair.953 · DOI · Paper page
- 10.1109/IJCNN.2008.4633969 · DOI · Paper page
- 10.1109/ICCV.2017.324 · DOI · Paper page
- 10.3390/sym13101769 · DOI
- 10.3389/fpls.2023.1330527 · DOI
- 10.1016/j.eja.2024.127400 · DOI
- 10.3389/fpls.2024.1521008 · DOI
- 10.1016/j.cropro.2024.106975 · DOI
- 10.3389/fpls.2024.1443815 · DOI
- 10.3390/su15118813 · DOI
- 10.1186/s13007-025-01349-w · DOI
- 10.1007/s13369-023-08280-z · DOI
- 10.3389/fpls.2024.1467811 · DOI
- 10.1016/j.scienta.2024.113079 · DOI
- 10.36001/ijphm.2024.v15i2.3993 · DOI
- Aftab, 2025, AI in oncology: Transforming cancer detection through machine learning and deep learning applications, arXiv:2501.15489 · arXiv
- 10.1186/s12911-025-02944-6 · DOI · Paper page
- 10.2196/53892 · DOI
- 10.3389/fneur.2025.1606149 · doi:10.3389/fneur.2025.1606149
- Solapure, 2024, Tomato leaf disease dataset
- 10.1109/CVPR.2017.243 · DOI · Paper page
- Simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556 · arXiv
- 10.1109/CVPR.2016.308 · DOI · Paper page
- 10.1109/CVPR.2017.195 · DOI · Paper page
- 10.1109/CVPR.2018.00474 · DOI · Paper page
- 10.1109/ICCV.2019.00140 · DOI · Paper page
- Tan, EfficientNet: Rethinking model scaling for convolutional neural networks, 6105
- Iandola, 2016, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 mb model size, arXiv:1602.07360 · arXiv
- Touvron, Training data-efficient image transformers & distillation through attention, 10347
- Cai, 2022, EfficientViT: Multi-scale linear attention for high-resolution dense prediction, arXiv:2205.14756 · arXiv
- Li, EfficientFormer: Vision transformers at MobileNet speed, 12263
- 10.18653/v1/N16-3020 · DOI · Paper page
- 10.5555/3454287.3455008 · doi:10.5555/3454287.3455008
- Marcel, 2010, Torchvision: Pytorch’s Computer Vision Library
- Wightman, 2019, Pytorch Image Models
- Lemaître, 2016, Imbalanced-learn: A Python toolbox to tackle the curse of imbalanced datasets in machine learning, J. Mach. Learn. Res., 18, 559
- 10.1109/TCYB.2021.3053165 · DOI · Paper page
- Jeffares, Joint training of deep ensembles fails due to learner collusion, 13559
- 10.1016/j.procs.2024.04.281 · DOI
Metadata
- Authors
- Hasan, M. J., Mazumdar, S., & Momen, S.
- Venue
- IEEE Access
- Published
- 2025
- Volume
- 13
- Pages
- 140313-140336
- ISSN
- 2169-3536
- Cited by
- 23
- References
- 7
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deployable Deep Learning for Cross-Domain Plant Leaf Disease Detection via Ensemble Learning, Knowledge Distillation, and Quantization. https://app.cochat.ai/papers/10.1109/access.2025.3595390
- The paper
- Hasan, M. J., Mazumdar, S., & Momen, S. (2025). Deployable Deep Learning for Cross-Domain Plant Leaf Disease Detection via Ensemble Learning, Knowledge Distillation, and Quantization. IEEE Access. https://doi.org/10.1109/access.2025.3595390
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.