Cross-Domain Transfer of Hyperspectral Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Theisen, Nick, Neubert, Peer
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911632429416448
author Theisen, Nick
Neubert, Peer
author_facet Theisen, Nick
Neubert, Peer
contents Hyperspectral imaging (HSI) semantic segmentation typically relies on in-domain training, but limited data availability often restricts model performance in real-world applications. Current approaches to leverage foundation models in proximal sensing use cross-modality techniques, bridging RGB and HSI to exploit vision foundation models. However, these methods either discard spectral information or introduce architectural complexity. We propose cross-domain transfer as an alternative, reusing HSI foundation models - originally trained in remote sensing - for proximal sensing applications. By eliminating the need to bridge modality gaps, our approach preserves spectral information while maintaining a simple architecture. Using the HS3-Bench benchmark, we systematically evaluate and compare conventional in-domain, in-modality training, cross-modality transfer and cross-domain transfer strategies. Our results demonstrate that cross-domain transfer achieves large performance improvements over in-domain, in-modality training, reduces the performance gap to cross-modality approaches and maintains strong performance in limited data settings. Thus, this work advances more effective HSI semantic segmentation in diverse applications.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26478
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Domain Transfer of Hyperspectral Foundation Models
Theisen, Nick
Neubert, Peer
Computer Vision and Pattern Recognition
Hyperspectral imaging (HSI) semantic segmentation typically relies on in-domain training, but limited data availability often restricts model performance in real-world applications. Current approaches to leverage foundation models in proximal sensing use cross-modality techniques, bridging RGB and HSI to exploit vision foundation models. However, these methods either discard spectral information or introduce architectural complexity. We propose cross-domain transfer as an alternative, reusing HSI foundation models - originally trained in remote sensing - for proximal sensing applications. By eliminating the need to bridge modality gaps, our approach preserves spectral information while maintaining a simple architecture. Using the HS3-Bench benchmark, we systematically evaluate and compare conventional in-domain, in-modality training, cross-modality transfer and cross-domain transfer strategies. Our results demonstrate that cross-domain transfer achieves large performance improvements over in-domain, in-modality training, reduces the performance gap to cross-modality approaches and maintains strong performance in limited data settings. Thus, this work advances more effective HSI semantic segmentation in diverse applications.
title Cross-Domain Transfer of Hyperspectral Foundation Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.26478