发表机构
School of Artificial Intelligence, Wuhan University; Wuhan AI Research; Institute of Automation, University of Chinese Academy of Sciences; Institute for Math & AI, Wuhan（武汉大学人工智能学院; 武汉人工智能研究院; 中国科学院大学自动化研究所; 武汉数学与人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出KnowChange框架，利用预训练视觉-语言模型实现知识引导的变化数据合成，其生成的紧凑规模数据在合成到真实迁移及增强任务中性能优于现有合成数据集，可提升合成数据下游效用。
AI 中文摘要
变化数据合成为扩充训练数据、提升变化检测模型性能提供了高性价比解决方案。然而，现有合成方法通常依赖手工规则模拟变化，类别转换的覆盖范围有限，限制了合成数据的多样性；同时，预定义的转换设计也限制了其适应不同变化类型的灵活性。本研究提出KnowChange，一种知识引导的变化数据合成框架，该框架利用预训练的视觉-语言模型作为知识源，从变化前场景和期望的变化类型中推理出合理的变化位置与类别转换。通过将知识引导的变化模拟与通用合成模型相结合，KnowChange可在统一框架内灵活合成多样化的变化类型。大量实验表明，KnowChange生成的数据即便规模紧凑，在合成到真实迁移及合成数据增强任务中，性能始终优于现有合成数据集。进一步分析显示，知识引导的变化模拟可无缝集成到现有合成流程中，提升合成数据的下游效用。
英文摘要
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.
Comments29 pages, 16 figures
