Advanced Deep Learning Framework for Soybean Leaf Disease Detection, Classification and Segmentation Using UAV Imagery
DOI:
https://doi.org/10.63682/jns.v14i3.9928Keywords:
Precision Agriculture, AI, Plant Disease Detection, SegmentationAbstract
Accurate and early detection of plant diseases is critical for sustainable agriculture and crop yield optimization. This study presents a unified deep learning framework for soybean disease classification, anomaly detection, and spatial localization using high-resolution UAV-based imagery. We adopt an attention-based Multi-Instance Learning (MIL) approach for image-level disease classification, enabling the model to focus on disease-relevant regions within heterogeneous field scenes using only image-level supervision. To detect both known and previously unseen disease patterns, we integrate a memory-based patch level anomaly detection mechanism that models healthy soybean appearance in feature space and identifies deviations via nearest-neighbor distances. Additionally, we employ a self-supervised contrastive segmentation pipeline to generate pixel-wise disease localization maps without requiring manual annotations. The proposed framework addresses key challenges in real-world agricultural monitoring, including label scarcity, mixed health states, and complex backgrounds. Extensive experiments demonstrate that the integration of MIL-based classification, memory-based anomaly detection, and self-supervised segmentation enables robust, scalable, and interpretable disease monitoring from UAV imagery, making the framework suitable for precision agriculture applications
Downloads
References
Strange, R.N., Scott, P.R.: Plant disease: a threat to global food security. Annual Review of Phytopathology 43, 83–116 (2005)
[2] Savary, S., Willocquet, L., Pethybridge, S.J., Esker, P., McRoberts, N., Nelson, A.: The global burden of pathogens and pests on major food crops. Nature Ecology & Evolution 3, 430–439 (2019)
[3] Mohanty, S.P., Hughes, D.P., Salath´e, M.: Using deep learning for image-based plant disease detection. Frontiers in Plant Science 7, 1419 (2016)
[4] Ferentinos, K.P.: Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture 145, 311–318 (2018)
[5] Janarthan, S., Thuseethan, S., Rajasegarar, S., Lyu, Q., Zheng, Y., Yearwood, J.: Liran: A lightweight residual attention network for in-field plant pest recognition. IEEE Transactions on AgriFood Electronics (2024)
[6] Wu, J., Abolghasemi, V., Anisi, M.H., Dar, U., Ivanov, A., Newenham, C.: Strawberry disease detection through an advanced squeeze-and-excitation deep learning model. IEEE Transactions on AgriFood Electronics 2(2), 259–267 (2024)
[7] Tsouros, D.C., Bibi, S., Sarigiannidis, P.: A review on uav-based applications for precision agriculture. Information 10(11), 349 (2019)
[8] Zhang, W., Li, H., Chen, M.: Uav-based crop disease detection: A review of imaging, methods, and applications. Computers and Electronics in Agriculture 215, 108513 (2024)
[9] Kamilaris, A., Prenafeta-Bold´u, F.X.: Deep learning in agriculture: A survey. Computers and Electronics in Agriculture 147, 70–90 (2018)
[10] Silva, J.A.O.S., Siqueira, V.S.d., Mesquita, M., et al.: Deep learning for weed detection and segmentation in agricultural crops using images captured by an unmanned aerial vehicle. Remote Sensing 16(23), 4394 (2024)
[11] Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9592–9600 (2019)
[12] Roth, L., Batzner, K., Schmitt, P.S., Eskofier, B., Zimmermann, D., Riess, C.: Towards total recall in industrial anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14318–14328 (2022)
[13] Hartman, G.L., West, E.D., Herman, T.K.: Soybean disease loss estimates for the united states and ontario, canada from 1996 to 2014. Plant Health Progress 16(5), 324–336 (2015)
[14] Dias, P.A., Tebbens, M.: Identification of soybean leaf diseases using uav images and deep learning. Remote Sensing 10(9), 1514 (2018)
[15] Jahin, A., Shahriar, S., Mridha, M.F., et al.: Soybean disease detection via interpretable hybrid cnn-gnn: Integrating mobilenetv2 and graphsage with cross-modal attention. arXiv preprint arXiv:2503.01284 (2025)
[16] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
[17] Brahimi, M., Boukhalfa, K., Moussaoui, A.: Deep learning for plant diseases: detection and saliency map visualisation. Human and Machine Learning, 93–117 (2018)
[18] Wang, X., Yu, Q., Yu, X., Lai, J.-H., Huang, R.: Self-supervised learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 44(9), 6654–6675 (2021)
[19] Cho, J.H., Mall, U., Bala, K., Hariharan, B.: Picie: Unsupervised semantic segmentation using invariance and equivariance in clustering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16794–16804 (2021)
[20] Hamilton, M., Zhang, Z., Hariharan, B., Freeman, W.T., Snavely, N.: Unsupervised semantic segmentation by distilling feature correspondences. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022)
[21] Gong, D., Liu, L., Le, V., Saha, B., Mansour, M.R., Venkatesh, S., Hengel, A.v.d.: Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1705–1714 (2019)
[22] Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning (ICML), pp. 1597–1607 (2020). PMLR
[23] He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9729–9738 (2020)
[24] Grill, J.-B., Strub, F., Altch´e, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B., Guo, Z.D., Azar, M.G., et al.: Bootstrap your own latent: A new approach to self-supervised learning. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 21271–21284 (2020)
[25] Rajesh, S.: Soybean Disease Image Dataset. https://data.mendeley.com/ datasets/hkbgh5s3b7/1
[26] He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
[27] Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 6105–6114 (2019). PMLR
[28] Schlegl, T., Seeb¨ock, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: f-anogan: Fast unsupervised anomaly detection with generative adversarial networks. Medical Image Analysis 54, 30–44 (2019)
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
