面向遥感图像检索的级联池化自注意力研究  

Cascade pooling self-attention research for remote sensing image retrieval

作　　者：吴刚 葛芸[1,2] 储珺 叶发茂[3] Wu Gang;Ge Yun;Chu Jun;Ye Famao(School of Software,Nanchang Hangkong University,Nanchang,Jiangxi 330063,China;Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition,Nanchang Hangkong University,Nanchang,Jiangxi 330063,China;School of Surveying and Mapping Engineering,East China University of Technology,Nanchang,Jiangxi 330013,China)

机构地区：[1]南昌航空大学软件学院,江西南昌330063 [2]南昌航空大学江西省图像处理与模式识别重点实验室,江西南昌330063 [3]东华理工大学测绘工程学院,江西南昌330013

出　　处：《光电工程》2022年第12期53-65,共13页Opto-Electronic Engineering

基　　金：国家自然科学基金资助项目(42261070,41801288,41261091,62162045);江西省自然科学基金资助项目(20202BAB212011)。

摘　　要：高分辨率遥感图像检索中,由于图像内容复杂,细节信息丰富,以致通过卷积神经网络提取的特征难以有效表达图像的显著信息。针对该问题,提出一种基于级联池化的自注意力模块,用来提高卷积神经网络的特征表达。首先,设计了级联池化自注意力模块,自注意力在建立语义依赖关系的基础上,可以学习图像关键的显著特征,级联池化是在小区域最大池化的基础上再进行均值池化,将其用于自注意力模块,能够在关注图像显著信息的同时保留图像重要的细节信息,进而增强特征的判别能力。然后,将级联池化自注意力模块嵌入到卷积神经网络中,进行特征的优化和提取。最后,为了进一步提高检索效率,采用监督核哈希对提取的特征进行降维,并将得到的低维哈希码用于遥感图像检索。在UC Merced、AID和NWPU-RESISC45数据集上的实验结果表明,本文方法能够有效提高检索性能。In high-resolution remote sensing image retrieval,due to the complex image content and rich detailed information,it is difficult for the features extracted by a convolutional neural network to effectively express the salient information of the image.In response to this issue,a self-attention module based on cascade pooling is proposed to improve the feature representation of convolutional neural networks.Firstly,a cascade pooling selfattention module is designed,and the self-attention module can learn key salient features of images on the basis of establishing semantic dependencies.Cascade pooling uses max pooling based on a small region,and then adopts average pooling based on the max pooled feature map.The cascade pooling is exploited in the self-attention module,which can keep important details of the image while paying attention to the salient information of the image,thereby enhancing feature discrimination.After that,the cascade pooled self-attention module is embedded into the convolutional neural network for feature optimization and extraction.Finally,in order to further improve the retrieval efficiency,supervised hashing with kernels is applied to reduce the dimensionality of features,and then the obtained low-dimensional hash code is utilized for remote sensing image retrieval.The experimental results on the UC Merced,AID and NWPU-RESISC45 data sets show that the proposed method can improve the retrieval performance effectively.

关 键 词：遥感图像检索 级联池化 自注意力模块 监督核哈希 卷积神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]