A Segmentation Map Difference-Based Domain Adaptive Change Detection Method

Deep neural network (DNN) has been widely used in remote sensing image change detection (CD) in recent years. Due to the scarcity of training data, a large number of labeled data onto other fields become the source of DNN concept learning in remote sensing image CD. However, the distribution of features of the CD data and other data varies greatly, which prevents DNN from being better applied for one task to another. To solve this problem, a domain adaptive CD method based on segmentation map difference is proposed to this article, which includes the pretraining stage and the CD stage. In the pretraining stage, the domain adaptive UNet (Ada-UNet) is applied as the basic network of remote sensing image segmentation for network training with the purpose of learning the concepts of different features. In the CD stage, strict threshold segmentation results are used to train the channel attention network, which makes it more efficient to utilize the high-dimensional feature map. The probabilistic map generated by the three-channel attention networks is evaluated, and then it is used to accurately classify the changing pixels. In this article, experiments are carried out on datasets with different feature distributions. The results show that this method has strong domain adaptability and can greatly reduce the influence of the difference in feature distributions of the CD results.