Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rolih, Blaž, Fučka, Matic, Wolf, Filip, Zajc, Luka Čehovin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908848726474752
author Rolih, Blaž
Fučka, Matic
Wolf, Filip
Zajc, Luka Čehovin
author_facet Rolih, Blaž
Fučka, Matic
Wolf, Filip
Zajc, Luka Čehovin
contents Unsupervised change detection (UCD) in remote sensing aims to localise semantic changes between two images of the same region without relying on labelled data during training. Most recent approaches rely either on frozen foundation models in a training-free manner or on training 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 that are dynamically estimated using feature statistics of target data, enabling diverse yet data-driven variation aligned with the target domain. It also easily extends to new modalities, such as SAR. MaSoN generalises strongly across diverse change types and achieves state-of-the-art performance on five benchmarks, improving the average F1 score by 14.1 percentage points. Project page: https://blaz-r.github.io/mason_ucd
format Preprint
id arxiv_https___arxiv_org_abs_2602_19881
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations
Rolih, Blaž
Fučka, Matic
Wolf, Filip
Zajc, Luka Čehovin
Computer Vision and Pattern Recognition
Artificial Intelligence
Unsupervised change detection (UCD) in remote sensing aims to localise semantic changes between two images of the same region without relying on labelled data during training. Most recent approaches rely either on frozen foundation models in a training-free manner or on training 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 that are dynamically estimated using feature statistics of target data, enabling diverse yet data-driven variation aligned with the target domain. It also easily extends to new modalities, such as SAR. MaSoN generalises strongly across diverse change types and achieves state-of-the-art performance on five benchmarks, improving the average F1 score by 14.1 percentage points. Project page: https://blaz-r.github.io/mason_ucd
title Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2602.19881