PAG-MSBNet:Prototype-aware gated multi-scale branch network for open-set crop disease recognition

Crop diseases pose a severe threat to global agricultural productivity and food security. While deep learning has revolutionized crop disease recognition, prevailing methods are currently constrained by a closed-set assumption, rendering them prone to overconfident errors when encountering unknown diseases in real-world open environments. To address this, we propose the Prototype-Aware Gated Multi-Scale Branch Network (PAG-MSBNet), a novel Open-Set Recognition (OSR) framework tailored to the unique challenges of crop disease imagery. Our approach features a multi-branch architecture that captures complementary fine-grained features through dedicated pathways. Each branch is equipped with a Multi-Scale Spatial-Channel Attention (MSSCA) module to enhance focus on polymorphic lesion regions across scales. Central to our framework is a Prototype-Aware Gating (PAG) mechanism, which dynamically fuses multi-branch predictions by evaluating their semantic alignment with learnable class prototypes, thereby enabling adaptive and robust feature integration. Comprehensive experiments on public benchmark datasets, including Paddy Doctor and PlantVillage, demonstrate that PAG-MSBNet consistently outperforms state-of-the-art OSR methods. It achieves superior performance in both closed-set classification accuracy and the crucial ability to reject unknown categories, while maintaining remarkable robustness across varying degrees of task openness. Our model provides a reliable and effective solution for practical crop disease diagnosis in complex agricultural settings. • We propose the PAG-MSBNet, a novel framework for open-set crop disease recognition. • A multi-branch architecture with MSSCA captures complementary discriminative features. • A Prototype-Aware Gating mechanism enables dynamic and semantic-aware feature fusion. • PAG-MSBNet outperforms state-of-the-art OSR methods on classical datasets • The model demonstrates strong robustness across varying levels of task openness.