用于高分辨遥感影像场景分类的迁移学习混合专家分类模型  

Transfer Learning Based Mixture of Experts Classification Model for High-Resolution Remote Sensing Scene Classification

作　　者：龚希[1] 陈占龙[1,2] 吴亮 谢忠[1,2] 徐永洋 Gong Xi;Chen Zhanlong;Wu Liang;Xie Zhong;Xu Yongyang(School of Geography and Information Engineering,China University of Geosciences,Wuhan,Hubei 430074,China;National Engineering Research Center of Geographic Information System,Wuhan,Hubei 430074,China)

机构地区：[1]中国地质大学(武汉)地理与信息工程学院,湖北武汉430074 [2]国家地理信息系统工程技术研究中心,湖北武汉430074

出　　处：《光学学报》2021年第23期11-23,共13页Acta Optica Sinica

基　　金：国家自然科学基金(42001340,U1711267,41871305);国家重点研发计划(2018YFB0505500,2018YFB0505504);地质探测与评估教育部重点实验室开放基金(GLAB2020ZR05);自然资源部城市国土资源监测与仿真重点实验室开放基金(KF-2020-05-068)。

摘　　要：针对小样本遥感影像场景数据集中地物多样性和分布复杂性引起的分类精度低下的问题,提出一种基于迁移学习的混合专家(TLMoE)分类模型。该模型通过多通道充分利用包含场景全局信息的全连接层特征和包含场景局部细节信息的卷积层特征,能够实现更精确的场景分类。基于全连接层特征的预判通道,利用场景全局信息完成对全部类别场景的初判;通过专家通道为每类场景训练专属专家网络,针对性地挖掘各类场景卷积层特征中蕴含的关键局部信息,提取可区分相似场景间细微差异的局部特征,完成细粒度的识别;结合预判权重实现顾及场景全局及局部差异的分类。在小样本数据集上的实验表明,本文方法可有效识别易混淆场景,能够取得较好的分类效果。To tackle the low classification accuracy caused by the diversity and distribution complexity of surface objects in small-sample datasets of remote sensing image scenes,this paper proposes a transfer learning based mixture of experts(TLMoE)classification model.The model can achieve more accurate scene classification by taking full advantage of the features from the convolution layer containing the local details and the fully-connected layer containing the global information of scenes through multi-channels.First,a pre-judgment channel based on the fully-connected layer features is established to preliminarily judge all kinds of scenes with global scene information;then exclusive expert networks are trained for each kind of scenes via the expert channel,which can mine the key local details contained in the convolution layer features of all categories of scenes targetedly and extract the local features used to distinguish the subtle differences between similar scenes to complete fine-grained identification.Finally,combined with the pre-judged weight,the model realizes the scene classification considering the global and local differences.Experiments on small-sample datasets show that the proposed method can effectively identify confusing scenes and achieve good classification results.

关 键 词：遥感 高分辨率遥感影像 场景分类 混合专家系统 迁移学习 

分 类 号：P237[天文地球—摄影测量与遥感]