南京信息工程大学学报2026，Vol.18Issue(1)：48-59,12.DOI:10.13878/j.cnki.jnuist.20250317003
基于强监督数据增强的双阶段扎把烟叶分级模型
A two-stage bundled tobacco grading model using strongly supervised data augmentation
摘要
Abstract
Using bundles as the grading unit for tobacco leaves is a key strategy to improve efficiency of tobacco procurement.However,due to occlusion and curling characteristics within the bundles,existing mainstream classifi-cation methods struggle to accurately extract their fine-grained features for grading.To address this,we propose a two-stage grading model for bundled tobacco leaves based on strongly supervised data augmentation.Our approach achieves precise grading in a progressive manner.First,a dual-attention residual network is designed to adaptively fuse multi-dimensional features for coarse-grained information extraction,and a soft channel attention module is pro-posed to generate attention maps highlighting key regions of the bundled leaves,thereby enabling coarse grading.Then,guided by these attention maps,we perform strongly supervised data augmentation on the global images to crop local images with distinctive features.This step facilitates a more refined grading by encouraging the network to fo-cus on discriminative fine-grained features.The proposed method is compared with current mainstream general and fine-grained classification approaches on a bundled tobacco leaf dataset.Experimental results show that the proposed method achieves a grading accuracy and macro-F1 score of 98.54%,significantly outperforming the compared meth-ods,and better meets the practical needs of industrial bundled tobacco leaf grading.关键词
烟叶分级/扎把烟叶/细粒度特征/强监督数据增强Key words
tobacco leaf grading/bundled tobacco leaves/fine-grained feature/strongly supervised data augmenta-tion分类
信息技术与安全科学引用本文复制引用
廖文静,黄剑满,杨洋,和红杰,陈帆..基于强监督数据增强的双阶段扎把烟叶分级模型[J].南京信息工程大学学报,2026,18(1):48-59,12.基金项目
国家自然科学基金(U1936113) （U1936113）
西南交通大学企业级纵向项目(R111624H01022) （R111624H01022）
