I-GhostNetV3: A Lightweight Deep Learning Framework for Vision-Sensor-Based Rice Leaf Disease Detection in Smart Agriculture.

Abstract

Accurate and timely diagnosis of rice leaf diseases is crucial for smart agriculture leveraging vision sensors. However, existing lightweight convolutional neural networks (CNNs) often struggle in complex field environments, where small lesions, cluttered backgrounds, and varying illumination complicate recognition. This paper presents I-GhostNetV3, an incrementally improved GhostNetV3-based network for RGB rice leaf disease recognition. I-GhostNetV3 introduces two modular enhancements with controlled overhead: (1) Adaptive Parallel Attention (APA), which integrates edge-guided spatial and channel cues and is selectively inserted to enhance lesion-related representations (at the cost of additional computation), and (2) Fusion Coordinate-Channel Attention (FCCA), a near-neutral SE replacement that enables efficient spatial-channel feature fusion to suppress background interference. Experiments on the Rice Leaf Bacterial and Fungal Disease (RLBF) dataset show that I-GhostNetV3 achieves 90.02% Top-1 accuracy with 1.831 million parameters and 248.694 million FLOPs, outperforming MobileNetV2 and EfficientNet-B0 under our experimental setup while remaining compact relative to the original GhostNetV3. In addition, evaluation on PlantVillage-Corn serves as a supplementary transfer sanity check; further validation on independent real-field target domains and on-device profiling will be explored in future work. These results indicate that I-GhostNetV3 is a promising efficient backbone for future edge deployment in precision agriculture.

Plant phenotyping relevance

画像からイネ葉の病徴を認識・分類する軽量深層学習手法を開発し、複数データセットで精度と計算量を評価しているため、植物フェノタイピング手法が中心である。

Code and data availability

The paper's phenotyping inputs are two publicly available plant image datasets explicitly linked by the authors: the RLBF rice leaf disease dataset on Mendeley Data (primary evaluation) and the PlantVillage-Corn dataset on GitHub (cross-domain transfer). No author analysis code or trained model checkpoints are stated.