Metraipolis › archive › dc_61852efdc3d5

Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data — arXiv:2609.03391

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03391
License (as archived)
CC0-1.0
Archived
2026-10-17T01:11:47.379Z
SHA-256 of the archived text
bb00f746c61f5e8a0ef825da12a57c16ed80b6bcbcd7d7b9e183621c8b356657
Stable URL of this page
https://metraipolis.com/documento/dc_61852efdc3d5

How to cite

Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data — arXiv:2609.03391 — arXiv (en), https://arxiv.org/abs/2609.03391 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_61852efdc3d5 (Metraipolis archive dc_61852efdc3d5, sha256 bb00f746c61f5e8a0ef825da12a57c16ed80b6bcbcd7d7b9e183621c8b356657)
BibTeX
@misc{dc61852efdc3d5,
  title = {Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data — arXiv:2609.03391},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03391},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_61852efdc3d5; sha256 bb00f746c61f5e8a0ef825da12a57c16ed80b6bcbcd7d7b9e183621c8b356657},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03391. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contrastive language-image learning (CLIP) has become a key paradigm for remote sensing vision-language understanding. However, existing remote sensing contrastive learning methods are mostly built on RGB-oriented CLIP architectures, making it difficult to exploit heterogeneous sensors such as SAR, multi-spectral imaging (MSI), and hyperspectral imaging (HSI). To address this limitation, we propose OmniRSCLIP, an end-to-end contrastive learning framework that supports multi-source sensor inputs for remote sensing vision-language modeling. The key idea is to extend CLIP beyond its fixed RGB input interface without breaking the pretrained visual knowledge. To this end, OmniRSCLIP introduces Spectral-Spatial Basis Decomposition (SSBD), which formulates arbitrary-channel adaptation as a basis recomposition problem: pretrained CLIP patch embeddings provide transferable spatial bases, while wavelength-conditioned coefficients span sensor-specific embedding kernels within a constrained visual prior space. This design avoids forcing heterogeneous sensors into a fixed-channel input space, while aligning them in a unified image-text semantic space. We further introduce a spectral-context-aware mask-based contrastive learning scheme to suppress modality-specific redundant features and enhance fine-grained image-text alignment. Finally, to support multi-modal training, we construct OmniRS5M, the first large-scale remote sensing image-text corpus covering RGB, SAR, MSI, and HSI. Experiments on retrieval, zero-shot classification, and semantic localization show that OmniRSCLIP preserves strong RGB-domain performance while effectively extending CLIP to heterogeneous remote sensing modalities.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.03391 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T00:28:02.948Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).