Self-Attention-Based Deep Feature Fusion for Remote Sensing Scene Classification
Self-Attention-Based Deep Feature Fusion for Remote Sensing Scene Classification
复制标题
DOI：
10.1109/lgrs.2020.2968550
复制
发表时间：
2021-01-01
影响因子：
4.8
通讯作者：
He, Nanjun
中科院分区：
文献类型：
--
作者：
Cao, Ran;Fang, Leyuan;He, Nanjun
遥感场景分类的目的是自动为每一幅航空影像赋予特定的语义标签。在本文中，我们提出了一种新的方法，称为基于自我注意的深度特征融合(SAFF)，用于聚集深层特征并强调遥感场景图像中复杂目标的权重，用于遥感场景分类。首先，应用预先训练好的卷积神经网络(CNN)模型从原始航空影像中提取抽象的多层特征地图。在此基础上，提出了空间加权和通道加权的非参数自关注层，增强了代表性对象的空间响应效果，更充分地利用了不常见的特征。因此，它可以提取更具区分性的特征。最后，将聚合后的特征送入支持向量机进行分类。在多个数据集上进行实验，结果证明了该方法在遥感场景分类中的有效性和高效性。
Remote sensing scene classification aims to assign automatically each aerial image a specific sematic label. In this letter, we propose a new method, called self-attention-based deep feature fusion (SAFF), to aggregate deep layer features and emphasize the weights of the complex objects of remote sensing scene images for remote sensing scene classification. First, the pretrained convolutional neural network (CNN) model is applied to extract the abstract multilayer feature maps from the original aerial imagery. Then, a nonparametric self-attention layer is proposed for spatial-wise and channel-wise weightings, which enhances the effects of the spatial responses of the representative objects and uses the infrequently occurring features more sufficiently. Thus, it can extract more discriminative features. Finally, the aggregated features are fed into a support vector machine (SVM) for classification. The proposed method is experimented on several data sets, and the results prove the effectiveness and efficiency of the scheme for remote sensing scene classification.