Unsupervised Remote Sensing Domain Adaptation Method with Adversarial Network and Auxiliary Task

• Main Authors: XU Suhui, MU Xiaodong, ZHANG Xiongmei, CHAI Dong
• Format: Article
• Language: zho
• Published: Surveying and Mapping Press 2017-12-01
• Series: Acta Geodaetica et Cartographica Sinica
• Subjects: remote sensing image; scene classification; domain adaptation; deep convolutional neural network; adversarial network; multi-task learning
• Online Access: http://html.rhhz.net/CHXB/html/2017-12-1969.htm

An important prerequisite when annotating the remote sensing images by machine learning is that there are enough training samples for training, but labeling the samples is very time-consuming. In this paper, we solve the problem of unsupervised learning with small sample size in remote sensing image scene classification by domain adaptation method. A new domain adaptation framework is proposed which combines adversarial network and auxiliary task. Firstly, a novel remote sensing scene classification framework is established based on deep convolution neural networks. Secondly, a domain classifier is added to the network, in order to learn the domain-invariant features. The gradient direction of the domain loss is opposite to the label loss during the back propagation, which makes the domain predictor failed to distinguish the sample's domain. Lastly, we introduce an auxiliary task for the network, which augments the training samples and improves the generalization ability of the network. The experiments demonstrate better results in unsupervised classification with small sample sizes of remote sensing images compared to the baseline unsupervised domain adaptation approaches.