Remote Sensing Image Retrieval by Multi-Scale Attention-Based CNN and Product Quantization
作者单位：School of AutomationBeijing Institute of Technology
会议名称：《第40届中国控制会议》
会议日期：2021年
学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 081002[工学-信号与信息处理] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
关 键 词：Remote Sensing(RS) Image Retrieval Product Quantization Multi-Scale Attention
摘 要：With the development of information technology,all kinds of image information are *** has been a hot is sue in computer vision to quickly retrieval interested images from data *** complexity of remote sensing images brings new challenges to the retrieval *** paper presents a new method for remote sensing image *** our proposed multiscale attention-based convolutional neural network with improved product quantization method（APQ）,we first use deep neural network with visual attention mechanism to extract feature representation of remote sensing images,and then we use an improved product quantization method to reduce the dimension of the features for the purpose of reducing the retrieval computation *** on two remote sensing datasets Satellite Remote Sensing and NWPU show that our APQ method can outperform some state-of-the-art remote sensing image retrieval methods.