Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent-Space Perturbations
TL;DR
Make some noise (MaSoN) is proposed, an end-to-end UCD framework that synthesizes diverse changes directly in the latent feature space during training, enabling diverse yet data-driven variation aligned with the target domain.
Abstract
Unsupervised change detection (UCD) aims to localize changes between two images of the same region without relying on labeled 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 generalize beyond a few change types, limiting their real-world usage, especially in rare or complex scenarios. To address this, we propose make some noise (MaSoN), an end-to-end UCD framework that synthesizes 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 generalizes strongly across diverse change types and improves the average $F1$ -score across five benchmarks by 14.1 percentage points (p.p.). Project page: https://blaz-r.github.io/mason_ucd/
