TD-SSCD: A Novel Network by Fusing Temporal and Differential Information for Self-Supervised Remote Sensing Image Change Detection
Yang Qu, Jiayi Li, Xin Huang, Dawei Wen
Abstract
Change detection of remote sensing images has a wide range of applications in many fields. In recent years, deep learning has become one of the most powerful tools for remote sensing change detection, thanks to its excellent feature learning capability. However, most deep learning methods require a lot of labeled data for the training, which is time-consuming and labor-intensive. Recently, a new learning paradigm—self-supervised learning—has become one of the hot topics in the field of change detection due to its ability to learn feature representations by training with a large amount of unlabeled data and without a large number of sample annotations. However, the existing methods for self-supervised learning are usually designed for natural image processing and are less considered for change detection in more complex scenes (e.g., remote sensing imagery). Therefore, in this paper, we propose a novel network by fusing temporal and differential information for self-supervised contrastive learning change detection, namely TD-SSCD. Specifically, TD-SSCD aims to mine information from the bi-temporal images and their differential images in a self-supervised learning framework, and it gradually learns the potential correlations between them through an alternating iteration learning strategy. The experimental results based on the OSCD and SZTAKI datasets show that the proposed method outperforms the current state-of-the-art unsupervised and self-supervised change detection methods. Benefiting from pre-training on unlabeled samples, the method closes the gap between unsupervised and supervised change detection.