Modified RefineNet with Attention-Based Fusion for Multi-Class Classification of Corn and Pepper Plant Diseases

Abstract

Early and precise detection of plant diseases is essential for safeguarding crop yield and ensuring sustainable agricultural practices. In this study, we propose the Modified RefineNet with Attention based Fusion (MoRefNet-AF), a Modified RefineNet architecture enhanced with attention-based fusion for multi-class classification of corn (maize) and Pepper leaf diseases. Unlike the original RefineNet, which was segmentation-oriented and computationally heavy, MoRefNet-AF is redesigned for lightweight and discriminative classification. The modifications include replacing standard convolutions with depthwise separable convolutions for efficiency, adopting the Mish activation function for smoother gradient flow, redesigning the multi-resolution fusion module with concatenation and shared convolution for richer cross-scale integration, and incorporating Squeeze-and-Excitation (SE) blocks for adaptive channel recalibration. Additionally, Chained Residual Pooling (CRP) with atrous convolutions enhances contextual representation, while global average pooling with dense layers improves classification readiness. When evaluated on a curated six-class dataset combining PlantVillage and Mendeley leaf disease repositories, MoRefNet-AF achieved 99.88% accuracy, 99.74% precision, 99.73% recall, 99.95% F1-score, and 99.73% specificity. These results outperform strong baselines including ResNet152V2, DenseNet201, EfficientNet-B0, and ConvNeXt-Tiny, while maintaining only 0.3 M parameters. With its compact design and TensorFlow Lite (v2.13) compatibility, MoRefNet-AF offers a robust, lightweight, and real-time deployable solution for precision agriculture and smart plant disease monitoring.

Plant phenotyping relevance

植物葉の病徴を画像から分類する軽量深層学習手法を開発し、複数データセットとベースラインで性能評価しているため、植物フェノタイピング手法が中心である。

Code and data availability

The supplied blocks describe a curated six-class dataset built from two pre-existing public repositories (PlantVillage via Kaggle and a Mendeley leaf disease dataset), but these are cited prior datasets, not paper-specific deposits. No author analysis code, trained model checkpoints, or supplementary data with an avail

No evidence-backed public reproduction asset is currently recorded.