aiqbench analysis
This research introduces MaSoN, a novel unsupervised remote sensing framework that synthesizes diverse change scenarios directly within the latent feature space rather than relying on predefined pixel-space rules or frozen foundation models. By dynamically estimating variations from target data statistics, the method significantly improves generalization across rare and complex scenarios while extending applicability to new modalities like SAR and multispectral imagery. The approach achieves a substantial 14.1 percentage point improvement in average F1 scores across five benchmarks, addressing critical limitations in current training-free or synthetic-change-dependent methods.
Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations
arXiv:2602.19881v2 Announce Type: replace-cross Abstract: 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/
Abstract: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: this https URL
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2602.19881 [cs.CV]
(or arXiv:2602.19881v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2602.19881 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1109/TGRS.2026.3730181 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 289 words
Related coverage
2026.9: There's room on this bus
Home Assistant · Sep 2, 2026
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
The Most Forbidden Technique is not always forbidden
LessWrong · Jul 18, 2026
News
Quantum Computing Report · Jul 25, 2026