An Efficient Attention-Enhanced MobileNetV2 Framework for Plant Disease Detection on Resource-Constrained Devices

Abstract

Leaf disease diagnosis needs models that are accurate enough for agronomic use yet small enough for constrained computing settings. This study examines a late-attention MobileNetV2 design in which one Convolutional Block Attention Module (CBAM) is inserted between the last MobileNetV2 convolutional map and global average pooling. The experiments use 54,306 controlled-background PlantVillage images spanning 38 classes. Under a uniform saved-model re-evaluation, MobileNetV2 + CBAM obtained 97.17% accuracy and 97.15% weighted F1-score, whereas MobileNetV2 obtained 96.78% and 96.73%. On the converted models, paired testing gave a 0.64-percentage-point accuracy advantage for the CBAM variant (95% CI: 0.31–0.96; exact McNemar p

Plant phenotyping relevance

植物葉の病徴を画像から検出する軽量深層学習モデルを開発・比較しており、植物病害状態の画像ベース表現型取得が中心である。

Code and data availability

The paper uses the public PlantVillage dataset (a pre-existing community resource, not a paper-specific deposit) and mentions a 'reproducibility package' with per-class metrics, confusion matrices, and prediction arrays, but no public URL, repository, or deposit identifier for the authors' code, models, or package is提供

No evidence-backed public reproduction asset is currently recorded.