针对植物病害识别，提出分离形状与纹理注意力的轻量模型。
STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification
- 分离形状与纹理注意力，分别用可变形卷积和Gabor滤波器捕捉病斑特征。
- 在CCMT数据集上达到89.00%准确率，参数仅401K，适合边缘设备部署。
- 无需训练的NAS设计+领域知识融合，适合农业视觉任务落地。
为应对日益增长的全球粮食安全需求，精准农业与基于深度学习的植物病害诊断变得至关重要。然而，在边缘设备上部署高精度模型仍具挑战性。现有轻量网络多采用通用目标识别注意力机制，难以捕捉病斑不规则形状和复杂纹理等细微病理特征。为此，我们提出两阶段解决方案：首先，采用无需训练的神经架构搜索方法（DeepMAD）构建适配边缘设备的高效网络主干；其次，引入形状-纹理注意力模块（STAM），将注意力分为两分支——一个使用可变形卷积（DCNv4）实现形状感知，另一个通过Gabor滤波器组实现纹理感知。在公开的CCMT植物病害数据集上，STA-Net模型（参数量401K，计算量51.1M FLOPs）达到89.00%准确率与88.96% F1分数。消融实验验证了STAM相比基线模型及标准注意力机制显著提升性能。通过解耦注意力并融入领域知识，为边缘部署的精准农业AI提供了可行路径。源代码见https://github.com/RzMY/STA-Net。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。