Single-temporal Supervised Remote Change Detection for Domain Generalization
This addresses the costly need for paired labeled data and domain-specific training in remote sensing change detection, offering a more practical solution, though it appears incremental as it builds on existing contrastive learning and AI-generated data techniques.
The paper tackles the problem of poor domain generalization and high data dependency in remote sensing change detection by proposing ChangeCLIP, a multimodal contrastive learning method with single-temporal AI-generated training, achieving superior generalization and outperforming state-of-the-art methods in experiments.
Change detection is widely applied in remote sensing image analysis. Existing methods require training models separately for each dataset, which leads to poor domain generalization. Moreover, these methods rely heavily on large amounts of high-quality pair-labelled data for training, which is expensive and impractical. In this paper, we propose a multimodal contrastive learning (ChangeCLIP) based on visual-language pre-training for change detection domain generalization. Additionally, we propose a dynamic context optimization for prompt learning. Meanwhile, to address the data dependency issue of existing methods, we introduce a single-temporal and controllable AI-generated training strategy (SAIN). This allows us to train the model using a large number of single-temporal images without image pairs in the real world, achieving excellent generalization. Extensive experiments on series of real change detection datasets validate the superiority and strong generalization of ChangeCLIP, outperforming state-of-the-art change detection methods. Code will be available.