Single-temporal Supervised Remote Change Detection for Domain Generalization

TL;DR

This paper introduces ChangeCLIP, a novel domain-generalized change detection method using visual-language pre-training, dynamic prompt optimization, and AI-generated single-temporal images, significantly improving cross-dataset performance.

Contribution

It proposes a new multimodal contrastive learning framework with a single-temporal training strategy for better domain generalization in remote change detection.

Findings

Outperforms state-of-the-art methods on multiple datasets

Demonstrates strong generalization ability across domains

Effective training with AI-generated single-temporal images

Abstract

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.