用真实与生成图像混合打造大地观测变化检测新数据集。
The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation
- 构建混合生成管道，融合真实与修复的遥感图像。
- 在五个场景中预训练模型，零样本到低数据都表现更优。
- 适合遥感、地球监测领域研究者，尤其关注数据稀缺问题。
基于超分辨率（VHR）影像的双时相变化检测对地球监测至关重要，但现有方法或依赖大量标注数据（语义场景），或仅适用于特定数据集（二值设定）。多数方法缺乏时空适应性：架构设计简单，且缺少在真实、全面数据集上的预训练。合成数据集是关键解决方案，但仍难以处理复杂多样的场景。本文提出 HySCDG，一个生成式流水线，可创建大规模混合语义变化检测数据集，包含真实与修复的VHR影像，以及双时相地表覆盖语义图和变化图。该方法在语义与空间引导下生成逼真图像，构建出综合性强且具备迁移鲁棒性的数据集 FSC-180k。我们在五个变化检测任务（二值与语义）中评估该数据集，涵盖零样本、混合及序列训练，并在低数据环境下测试。实验表明，基于该混合数据集预训练可显著提升性能，在所有配置下均优于完全合成数据集 SyntheWorld。全部代码、模型与数据已公开：https://yb23.github.io/projects/cywd/
原文摘要 · Abstract (English)
Bi-temporal change detection at scale based on Very High Resolution (VHR) images is crucial for Earth monitoring. This remains poorly addressed so far: methods either require large volumes of annotated data (semantic case), or are limited to restricted datasets (binary set-ups). Most approaches do not exhibit the versatility required for temporal and spatial adaptation: simplicity in architecture design and pretraining on realistic and comprehensive datasets. Synthetic datasets are the key solution but still fail to handle complex and diverse scenes. In this paper, we present HySCDG a generative pipeline for creating a large hybrid semantic change detection dataset that contains both real VHR images and inpainted ones, along with land cover semantic map at both dates and the change map. Being semantically and spatially guided, HySCDG generates realistic images, leading to a comprehensive and hybrid transfer-proof dataset FSC-180k. We evaluate FSC-180k on five change detection cases (binary and semantic), from zero-shot to mixed and sequential training, and also under low data regime training. Experiments demonstrate that pretraining on our hybrid dataset leads to a significant performance boost, outperforming SyntheWorld, a fully synthetic dataset, in every configuration. All codes, models, and data are available here: https://yb23.github.io/projects/cywd/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。