SAR Image Retrieval Based on Unsupervised Domain Adaptation and Clustering

Efficiently retrieving synthetic aperture radar (SAR) image is an important yet challenging task in the remote sensing field. Due to the shortage of labeled SAR images for fine-tuning convolutional neural network (CNN) models, this letter presents an unsupervised domain adaptation model based on CNN to learn the domain-invariant feature between SAR images and optical aerial images for SAR image retrieving, which can alleviate the burden of manual labeling. We extend a deep CNN to a novel adversarial network by adding the domain discriminator and the pseudolabel predictor. We improve the adaptation capacity of the adversarial network by utilizing the class information of SAR training images, which is obtained by clustering. Compared with the other related methods, the proposed method can enhance retrieval performance with our SAR data set.