STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification
This work addresses the problem of lightweight plant disease diagnosis for precision agriculture, offering an incremental improvement by integrating domain-specific attention mechanisms.
The paper tackled the challenge of deploying high-precision plant disease classification models on edge devices by proposing STA-Net, which uses a decoupled shape and texture attention module to capture subtle pathological features, achieving 89.00% accuracy and an F1 score of 88.96% on the CCMT dataset.
Responding to rising global food security needs, precision agriculture and deep learning-based plant disease diagnosis have become crucial. Yet, deploying high-precision models on edge devices is challenging. Most lightweight networks use attention mechanisms designed for generic object recognition, which poorly capture subtle pathological features like irregular lesion shapes and complex textures. To overcome this, we propose a twofold solution: first, using a training-free neural architecture search method (DeepMAD) to create an efficient network backbone for edge devices; second, introducing the Shape-Texture Attention Module (STAM). STAM splits attention into two branches -- one using deformable convolutions (DCNv4) for shape awareness and the other using a Gabor filter bank for texture awareness. On the public CCMT plant disease dataset, our STA-Net model (with 401K parameters and 51.1M FLOPs) reached 89.00% accuracy and an F1 score of 88.96%. Ablation studies confirm STAM significantly improves performance over baseline and standard attention models. Integrating domain knowledge via decoupled attention thus presents a promising path for edge-deployed precision agriculture AI. The source code is available at https://github.com/RzMY/STA-Net.