Metraipolis › archive › dc_cb577c926a4c

On the Effectiveness of Adaptation Strategies for VLM-Based Federated Learning in Remote Sensing — arXiv:2608.04791

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04791
License (as archived)
CC0-1.0
Archived
2026-10-31T11:48:09.401Z
SHA-256 of the archived text
37695224fde1d542447199f16ced2eb8b7e4cb3ffd8046734ff88252dfc10ce1
Stable URL of this page
https://metraipolis.com/documento/dc_cb577c926a4c

How to cite

On the Effectiveness of Adaptation Strategies for VLM-Based Federated Learning in Remote Sensing — arXiv:2608.04791 — arXiv (en), https://arxiv.org/abs/2608.04791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb577c926a4c (Metraipolis archive dc_cb577c926a4c, sha256 37695224fde1d542447199f16ced2eb8b7e4cb3ffd8046734ff88252dfc10ce1)
BibTeX
@misc{dccb577c926a4c,
  title = {On the Effectiveness of Adaptation Strategies for VLM-Based Federated Learning in Remote Sensing — arXiv:2608.04791},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04791},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb577c926a4c; sha256 37695224fde1d542447199f16ced2eb8b7e4cb3ffd8046734ff88252dfc10ce1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated learning (FL) enables collaborative training of deep learning models across decentralized image archives without requiring data centralization. This paradigm is particularly relevant in remote sensing (RS), where legal regulations, privacy concerns, and bandwidth constraints restrict data sharing. However, the presence of training data heterogeneity across clients (known as non-IID data) can impede convergence and limit the generalization capability of the aggregated global model. To mitigate the adverse effects of training data heterogeneity, vision-language models (VLMs) can be leveraged in FL due to their transferable representations, which have demonstrated robustness under distribution shifts. However, their large parameter size may substantially increase communication overhead and local computational complexity in federated settings. Therefore, it is crucial to select an appropriate VLM adaptation strategy that balances the generalization ability with the communication and computational constraints. To address this issue, in this paper, we present the first comparative study of VLM adaptation strategies for FL in the context of RS image classification. We investigate full fine-tuning, encoder-specific fine-tuning, prompt learning, and low-rank adaptation (LoRA) tuning, and analyze them with respect to three criteria: 1) generalization capability under non-IID data, 2) communication overhead, and 3) local computational complexity. Experiments on BigEarthNet-S2, EuroSAT, RESISC45, and ImageNet reveal distinct trade-offs between task specialization, cross-domain generalization, and efficiency. Based on our findings, we derive a guideline for the selection of an appropriate VLM adaptation strategy in FL for RS image classification under different operational constraints. The code of this work is publicly available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.04791 — 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 2026-10-31T11:37:40.715Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).