A Self-Supervised Learning Pretraining Framework for Remote Sensing Image Change Detection

In recent years, change detection (CD) has achieved remarkable success through the use of deep learning. However, most existing methods rely on label teaching and thus have many limitations when dealing with the complexity and diversity of remote sensing (RS) scenes. In this work, we propose a self-supervised learning (SSL) pretraining framework for RS image CD (SSLCD). Our motivation is to leverage the intrinsic structure of multitemporal data to learn general and robust representations, generating competitive pretrained models for the CD task. On the one hand, an intrinsic structure learning (ISL) strategy is introduced, which enforces feature invariance and change consistency across temporal phases and augmented views, learning discriminatory representations related to changes while simultaneously mitigating noises associated with irrelevant changes. On the other hand, a self/cross-reconstruction (SCR) mechanism is proposed, which extends masked image modeling (MIM) to multitemporal images by predicting missing parts of the pre-phase image using the post-phase image, thereby enhancing the model’s capacity in modeling high-level contextual information. Finally, models pretrained using SSLCD are extensively evaluated on three CD datasets, and the results demonstrate that SSLCD outperforms existing RS pretraining methods and the state-of-the-art CD methods.