Search papers, labs, and topics across Lattice.
This paper introduces KnowChange, a novel framework for change data synthesis in remote sensing that utilizes pretrained vision-language models to enhance the diversity and flexibility of synthesized change data. By moving away from handcrafted rules, KnowChange allows for more plausible change simulations based on real-world knowledge, resulting in improved performance for change detection models. Experimental results reveal that data generated through KnowChange significantly outperforms traditional synthetic datasets in both transfer learning and data augmentation scenarios, even when produced at a smaller scale.
Knowledge-guided change synthesis can dramatically enhance the realism and utility of synthetic data for remote sensing applications.
Change data synthesis provides a cost-effective solution for expanding training data and improving the performance of change detection models. However, existing synthesis methods typically rely on handcrafted rules to simulate changes, where limited coverage of class transitions restricts the diversity of synthesized data, while predefined transition designs limit their flexibility in accommodating varied change types. In this work, we introduce KnowChange, a knowledge-guided change data synthesis framework that leverages pretrained vision-language models as knowledge sources to reason about plausible change locations and class transitions from pre-change scenes and desired change types. By integrating knowledge-guided change simulation with generalizable synthesis models, KnowChange enables flexible synthesis of diverse change types within a unified framework. Extensive experiments demonstrate that KnowChange-generated data consistently outperforms existing synthetic datasets in both synthetic-to-real transfer and synthetic data augmentation, despite being generated at a compact scale. Further analyses show that the knowledge-guided change simulation can be seamlessly integrated into existing synthesis pipelines and enhance the downstream utility of synthesized data.
