Multi Scale Vision Transformer for Enhancing EfficientnetB3 based Leaf Disease Classification
Agricultural Science Digest - A Research Journal · 24.06.2026 · (Of)
DOI: 10.18805/ag.d-6517 ↗Kurz gefasst
Fachartikel in der Zeitschrift Agricultural Science Digest - A Research Journal, online erschienen am 24.06.2026. Verfasst von Goli Laxmi Prasanna und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Background
Early prediction in plant diseases enables timely management, reducing crop losses and promoting healthier yields. Deep learning (DL) models are effective tools for an early prediction of plant diseases. Although among these, EfficientNetB3 based models outperform for multi-class plant disease classification but is highly sensitive to noisy or poor-quality input data, such as images with background clutter, varying lighting conditions, or partially damaged leaves and may lead to incorrect classification results, reducing the model’s reliability in real-world agricultural scenarios.
Methods
To overcome these limitations, a multi-scale vision transformer (MSViT) model is proposed to capture multi-scale features for enhancing robustness against noise and background variations. A multi-stage ViT structure is implemented to extract hierarchical image features, while enhanced convolution layers are used to down sample the output of each stage, enabling feature extraction at multiple scales. The size and stride of the convolution kernel are dynamically adjusted according to feature dimensionality to ensure effective representation learning across scales. To reduce the computational complexity, window attention is introduced in each ViT stage with window sizes that vary in proportion to feature dimensions. The multi scale features obtained from different stages are then fused using a feature pyramid network (FPN) to strengthen the localization and representation of disease affected regions. For classification, a modified EfficientNet-B3 model is used to predict diseases. The complete framework is termed as multi-scale vision transformer for EfficientNetB3 (MSViT-EfficientNetB3).
Result
Finally, the proposed model achieves 94.2% of accuracy on Plant Village dataset outperforming existing models in multi class plant disease classification.
Zitieren
APA
Prasanna, G. L., & Nagarajan, S. (2026). Multi Scale Vision Transformer for Enhancing EfficientnetB3 based Leaf Disease Classification. Agricultural Science Digest - A Research Journal. https://doi.org/10.18805/ag.d-6517
Vancouver
Prasanna GL, Nagarajan S. Multi Scale Vision Transformer for Enhancing EfficientnetB3 based Leaf Disease Classification. Agricultural Science Digest - A Research Journal. 2026. doi:10.18805/ag.d-6517
BibTeX
@article{Prasanna2026,
author = {Prasanna, Goli Laxmi and Nagarajan, S.},
title = {Multi Scale Vision Transformer for Enhancing EfficientnetB3 based Leaf Disease Classification},
journal = {Agricultural Science Digest - A Research Journal},
year = {2026},
number = {Of},
doi = {10.18805/ag.d-6517}
}
EUVIMED