Metraipolis › archive › dc_86dc0e683062

GeoJeV: Unified Spatial Probability for Training-Free Efficient Evidence Acquisition in Ultra-High-Resolution Remote Sensing — arXiv:2611.08879

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.08879
License (as archived): CC0-1.0
Archived: 2026-11-09T22:45:08.067Z
SHA-256 of the archived text: 22029c28a595a78af700ce987343d77272c02d2f2638790674dd1f0e6c220701
Stable URL of this page: https://metraipolis.com/documento/dc_86dc0e683062

How to cite

GeoJeV: Unified Spatial Probability for Training-Free Efficient Evidence Acquisition in Ultra-High-Resolution Remote Sensing — arXiv:2611.08879 — arXiv (en), https://arxiv.org/abs/2611.08879 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86dc0e683062 (Metraipolis archive dc_86dc0e683062, sha256 22029c28a595a78af700ce987343d77272c02d2f2638790674dd1f0e6c220701)

BibTeX

@misc{dc86dc0e683062,
  title = {GeoJeV: Unified Spatial Probability for Training-Free Efficient Evidence Acquisition in Ultra-High-Resolution Remote Sensing — arXiv:2611.08879},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08879},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86dc0e683062; sha256 22029c28a595a78af700ce987343d77272c02d2f2638790674dd1f0e6c220701},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08879. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Ultra-high-resolution (UHR) remote sensing imagery provides rich spatial details but poses challenges for accurate and efficient multimodal understanding. Existing evidence acquisition methods selectively explore relevant image regions, yet largely rely on generative multimodal large language models (MLLMs) for intermediate search control. However, reinforcement learning from human feedback (RLHF) primarily aligns these models with human-preferred responses rather than explicitly optimizing region-level relevance judgments, while repeated autoregressive decoding introduces additional computational overhead. To address these limitations, we propose GeoJeV, a training-free method that formulates evidence acquisition as spatial probability-driven decision making. At each evaluated region, a frozen JeV model produces a probability distribution over candidate regions. Specifically, Region Rank prioritizes candidate regions, Sparse Branch adaptively determines branching width through sparse probability support, and Depth Gate controls refinement depth based on branch sparsity and distribution concentration. By coordinating search priority, branching width, and refinement depth through a shared distribution, GeoJeV reduces reliance on RLHF-aligned generation and eliminates intermediate decoding. Experiments on LRS-GRO, MME-RealWorld-RS, and LRS-VQA achieve accuracies of 60.59%, 52.79%, and 34.32%, respectively. Across the three benchmarks, GeoJeV improves the average accuracy of Qwen3-VL-8B by +5.32pp with only 1.12 additional seconds per question, while achieving a 7.8-fold inference speedup over the recent method.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2611.08879 — 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 2026-11-09T22:37:47.207Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).