aiqbench analysis
This research applies flow matching, a deep generative technique, to solve the domain shift problem in satellite radiometer imagery without requiring large labeled datasets. By leveraging deterministic ordinary differential equations conditioned on specific instruments, the method achieves precise alignment for improved rain precipitation estimation across the GPM-Core constellation. The work highlights a significant advancement in unsupervised adaptation for Earth observation tasks using advanced generative models.
Unsupervised Domain Adaptation for Enhanced Radiometer Image Precipitation Estimation using Conditional Flow Matching
arXiv:2610.01890v1 Announce Type: cross Abstract: Deep generative networks have recently achieved unprecedented performance in precise image and video editing using sophisticated textual prompts. However, the effectiveness of such models heavily depends on access to very large supervised and annotated image datasets, which can be very difficult to obtain. This is particularly true for satellite instruments, which very rarely overlap with labelled data, and suffer from domain shifts in the rare occasions they do. In this paper, we investigate the potential of flow matching models for unsupervised domain adaptation of satellite radiometer images. Our main contribution is a novel unsupervised method that achieves precise domain alignment by leveraging parts of the deterministic ordinary differential equations in flow matching models, conditioned on different satellite instruments. A key strength of our approach is its ability to preserve essential information while adapting across any domains since the perturbations are in theory bijective. Extensive experiments conducted on the GPM-Core constellation show the benefit of our conditional domain adaptation, particularly in improving rain precipitation estimation from radiometer imagery.
Abstract:Deep generative networks have recently achieved unprecedented performance in precise image and video editing using sophisticated textual prompts. However, the effectiveness of such models heavily depends on access to very large supervised and annotated image datasets, which can be very difficult to obtain. This is particularly true for satellite instruments, which very rarely overlap with labelled data, and suffer from domain shifts in the rare occasions they do. In this paper, we investigate the potential of flow matching models for unsupervised domain adaptation of satellite radiometer images. Our main contribution is a novel unsupervised method that achieves precise domain alignment by leveraging parts of the deterministic ordinary differential equations in flow matching models, conditioned on different satellite instruments. A key strength of our approach is its ability to preserve essential information while adapting across any domains since the perturbations are in theory bijective. Extensive experiments conducted on the GPM-Core constellation show the benefit of our conditional domain adaptation, particularly in improving rain precipitation estimation from radiometer imagery.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.01890 [cs.CV]
(or arXiv:2610.01890v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.01890 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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 · 267 words
Related coverage
HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors
arXiv · Aug 17, 2026
Distilling Image Prototypes for Guided Test-Time Adaptation
arXiv · Sep 11, 2026
Dual Variational Autoencoders for Efficient Sim-to-Real Transfer in Low-Cost Robotic Navigation
arXiv · Oct 6, 2026
Multi-Pass, Multi-View Blended Learning for High-Fidelity Volumetric CT Synthesis from Chest X-Rays
arXiv · Sep 10, 2026