在潜在空间生成数据驱动的变更，提升无监督遥感变化检测泛化能力
Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations
- 在潜在空间动态生成变化，基于目标数据特征统计自适应合成
- 跨五项基准平均F1提升14.1个百分点，显著优于现有方法
- 无需预设变化类型，适用于复杂或罕见场景，可扩展至SAR等多模态
无监督遥感变化检测（UCD）旨在不依赖标注数据的情况下定位两幅同一区域图像之间的变化。当前多数方法要么采用冻结的基础模型进行零训练，要么在像素空间生成合成变化。这两种策略均依赖于预设的变化类型假设，通常通过手工规则、外部数据集或辅助生成模型引入。由于这些假设，现有方法在多样变化类型上泛化能力差，限制了实际应用，尤其在罕见或复杂场景中。为此，我们提出MaSoN（Make Some Noise），一个端到端的无监督变化检测框架，直接在训练过程中通过目标数据特征统计动态估计，在潜在特征空间合成多样化变化。该方法生成的变化既丰富又与目标域数据一致，且由于在潜在空间操作，天然支持新模态扩展，如雷达（SAR）和多光谱数据。MaSoN在五个基准测试中平均F1得分提升14.1个百分点，表现出强泛化能力。
原文摘要 · Abstract (English)
Unsupervised remote sensing change detection (UCD) aims to localise changes between two images of the same region without relying on labelled training data. Most recent approaches either use a frozen foundation model in a training-free manner or train with synthetic changes generated in pixel space. Both strategies inherently rely on predefined assumptions about change types, typically introduced through handcrafted rules, external datasets, or auxiliary generative models. Due to these assumptions, such methods fail to generalise beyond a few change types, limiting their real-world usage, especially in rare or complex scenarios. To address this, we propose MaSoN (Make Some Noise), an end-to-end UCD framework that synthesises diverse changes directly in the latent feature space during training. It generates changes dynamically estimated from feature statistics of the target data, enabling diverse yet data-driven variation aligned with the target domain. Since synthesis happens in latent space, it also easily extends to new modalities, such as SAR and multispectral data. MaSoN generalises strongly across diverse change types and improves the average F1 score across five benchmarks by 14.1 percentage points. Project page: https://blaz-r.github.io/mason_ucd/
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。