Plant disease classification in the wild using vision transformers and mixture of experts
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Plant disease classification using deep learning techniques has shown promising results, especially when models are trained on high-quality images. However, these models often suffer from a significant drop in their accuracies when tested in real-world agricultural settings. In the wild, models encounter images that are significantly different from the training data in aspects like lighting conditions, capturing conditions, image resolution, and the severity of disease. This discrepancy between the training images and images in-the-wild conditions poses a major challenge for deploying these models in agricultural settings. In this paper, we present a novel approach to address this issue by combining a Vision Transformer backbone with a Mixture of Experts, where multiple expert models are trained to specialize in different aspects of the input data, and a gating mechanism is implemented to select the most relevant experts for each input. The use of Mixture of Experts allows the model to dynamically allocate specialized experts to different types of input data, improving model performance across diverse image conditions. The approach significantly improves performance on diverse datasets that contain a range of image capturing conditions and disease severities. Furthermore, the model incorporates entropy regularization and orthogonal regularization, aiming to enhance the robustness and generalization capabilities. Experimental results demonstrate that the proposed model achieved a 20% improvement in accuracy compared to Vision Transformer (ViT). Furthermore, it demonstrated a 68% accuracy on cross-domain datasets like PlantVillage to PlantDoc, surpassing baseline models such as InceptionV3 and EfficientNet. This highlights the potential of our model for effective deployment in dynamic agricultural environments.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., & Dean, J. (2017) · arXiv · doi:10.48550/arxiv.1701.06538 · Cited by 933
TransFG: A Transformer Architecture for Fine-Grained Recognition
He, J., Chen, J.-N., Liu, S., Kortylewski, A., Yang, C., Bai, Y., & Wang, C. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19967 · Cited by 551
Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., Casas, D. D. L., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.06825 · Cited by 340 · cited 1×
“5 (Jiang et al., 2023).”
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., & Beyer, L. (2021) · arXiv · doi:10.48550/arxiv.2106.10270 · Cited by 292 · cited 1×
“To address this, we incorporate usage regularization (Steiner et al., 2021), which penalizes the under-utilization of experts and encourages the gating mechanism to distribute inputs more evenly.”
Research works printed but not linked: 25
- Arnal Barbedo, 2013, Digital image processing techniques for detecting, quantifying and classifying plant diseases, SpringerPlus, 2, 660, 10.1186/2193-1801-2-660 · DOI · Paper page
- Bansal, 2018, Can we gain more from orthogonality regularizations in training deep networks, Adv. Neural Inf. Process. Syst., 31, 10.48550/arXiv.1706.03762 · DOI · Paper page
- Ferentinos, 2018, Deep learning models for plant disease detection and diagnosis, Comput. Electron. Agric., 145, 311, 10.1016/j.compag.2018.01.009 · DOI · Paper page
- Girshick, 2014, Rich feature hierarchies for accurate object detection and semantic segmentation, Proc. IEEE Conf. Comput. Vision Pattern Recognit., 580, 10.1109/CVPR.2014.81 · DOI · Paper page
- Grandvalet, 2004, Semi-supervised learning by entropy minimization, Adv. Neural Inf. Process. Syst., 17
- He, 2016, Deep residual learning for image recognition, 770
- Huang, 2017, Densely connected convolutional networks, Proc. IEEE Conf. Comput. Vision Pattern Recognit., 4700, 10.1109/CVPR35066.2017 · DOI · Paper page
- Huang, 2023, Towards moe deployment: Mitigating inefficiencies in mixture-of-expert (moe) inference, arXiv preprint arXiv:2303.06182, 10.1109/CVPR.2017.243 · DOI · Paper page
- Hughes, 2015, An open access repository of images on plant health to enable the development of mobile disease diagnostics, arXiv preprint arXiv:1511.08060, 10.48550/arXiv.1511.08060 · arXiv · doi:10.48550/arxiv.1511.08060 · Paper page
- Kamilaris, 2018, Deep learning in agriculture: A survey, Comput. Electron. Agric., 147, 70, 10.1016/j.compag.2018.02.016 · DOI · Paper page
- Kullback, 1951, On information and sufficiency, Ann. Math. Stat, 22, 79, 10.1214/aoms/1177729694 · DOI · Paper page
- Mohanty, 2016, Using deep learning for image-based plant disease detection, Front. Plant Sci., 7, 10.3389/fpls.2016.01419 · DOI · Paper page
- Muhammad, 2023, Harnessing the power of diffusion models for plant disease image augmentation, Front. Plant Sci., 14, 10.3389/fpls.2023.1280496 · DOI
- Picon, 2019, Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild, Comput. Electron. Agric., 161, 280, 10.1016/j.compag.2018.04.002 · DOI · Paper page
- Rao, 2021, Counterfactual attention learning for fine-grained visual categorization and re-identification, 1025
- Redmon, 2016, You only look once: Unified, real-time object detection, 779
- Salman, 2023, Crop-saving with ai: latest trends in deep learning techniques for plant pathology, Front. Plant Sci., 14, 10.3389/fpls.2023.1224709 · DOI
- Simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556, 10.1109/ACPR.2015.7486599 · DOI · Paper page
- Singh, 2020, Plantdoc: a dataset for visual plant disease detection, 249, 10.1145/3371158.3371196 · DOI · Paper page
- Sladojevic, 2016, Deep neural networks based recognition of plant diseases by leaf image classification, Comput. Intell. Neurosci., 2016, 3289801, 10.1155/2016/3289801 · DOI · Paper page
- Szegedy, 2015, Going deeper with convolutions. In, Proc. IEEE Conf. Comput. Vision Pattern Recognit., 1, 10.1109/CVPR.2015.7298594 · DOI · Paper page
- Tan, 2019, Efficientnet: Rethinking model scaling for convolutional neural networks, 6105
- Van der Maaten, 2008, Visualizing data using t-sne, J. Mach. Learn. Res., 9
- Vaswani, 2017, Attention is all you need
- Zhuang, 2020, Learning attentive pairwise interaction for fine-grained classification, 13130
Metadata
- Authors
- Salman, Z., Muhammad, A., & Han, D.
- Venue
- Frontiers in Plant Science
- Publisher
- Frontiers Media SA
- Published
- 2025-06-18
- Volume
- 16
- ISSN
- 1664-462X
- Cited by
- 60
- References
- 5
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
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.