激光与光电子学进展, 2019, 56 (11): 112801, 网络出版: 2019-06-13
基于深度对抗域适应的高分辨率遥感影像跨域分类 下载: 1497次
Deep Adversarial Domain Adaptation Method for Cross-Domain Classification in High-Resolution Remote Sensing Images
遥感 场景分类 无监督域适应 卷积神经网络 生成对抗网络 remote sensing scene classification unsupervised domain adaptation convolutional neural network generative adversarial networks
摘要
提出一种基于深度对抗域适应的高分辨率遥感影像跨域分类方法。利用深度卷积神经网络VGG16(Visual Geometry Group)学习场景影像的深度特征,然后利用对抗学习方法最小化源域和目标域特征分布差异。利用RSI-CB256(Remote Sensing Image Classification Benchmark)、NWPU-RESISC45(Northwestern Polytechnical University Remote Sensing Image Scene Classification)和AID(Aerial Image data set)数据集构建源域数据集,并将UC-Merced(University of California, Merced)和WHU-RS 19(Wuhan University Remote Sensing)两个数据集作为目标域数据集进行实验,实验结果表明,所提方法在目标域数据集没有标签的情况下,能够提高模型对目标域数据集的泛化能力。
Abstract
In this study, a deep adversarial domain adaptation method is proposed for cross-domain classification in high-resolution remote sensing images. A deep convolutional neural network VGG16 is used to learn the deep features of scene images. The adversarial learning method is used to minimize the difference of feature distribution between source and target domains. RSI-CB256(Remote Sensing Image Classification Benchmark), NWPU-RESISC45(Northwestern Polytechnical University Remote Sensing Image Scene Classification)and AID(Aerial Image data set) are used as source domain datasets, and UC-Merced(University of California, Merced)and WHU-RS 19(Wuhan University Remote Sensing)are used as target domain datasets. The experimental results denote that the proposed method can improve the generalization ability of the model for target domain dataset without labels.
滕文秀, 王妮, 陈泰生, 王本林, 陈梦琳, 施慧慧. 基于深度对抗域适应的高分辨率遥感影像跨域分类[J]. 激光与光电子学进展, 2019, 56(11): 112801. Wenxiu Teng, Ni Wang, Taisheng Chen, Benlin Wang, Menglin Chen, Huihui Shi. Deep Adversarial Domain Adaptation Method for Cross-Domain Classification in High-Resolution Remote Sensing Images[J]. Laser & Optoelectronics Progress, 2019, 56(11): 112801.