Metraipolis › archive › dc_8124db13bd91

EarthJev: Efficient Visual Evidence Acquisition and Decision for UHR Remote Sensing Understanding — arXiv:2611.10005

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10005
License (as archived)
CC0-1.0
Archived
2026-11-10T18:42:07.508Z
SHA-256 of the archived text
3dca7e309461cc8f4ce137a375dee3dd10a49ce725c3bb7fd7824d18973b9f43
Stable URL of this page
https://metraipolis.com/documento/dc_8124db13bd91

How to cite

EarthJev: Efficient Visual Evidence Acquisition and Decision for UHR Remote Sensing Understanding — arXiv:2611.10005 — arXiv (en), https://arxiv.org/abs/2611.10005 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8124db13bd91 (Metraipolis archive dc_8124db13bd91, sha256 3dca7e309461cc8f4ce137a375dee3dd10a49ce725c3bb7fd7824d18973b9f43)
BibTeX
@misc{dc8124db13bd91,
  title = {EarthJev: Efficient Visual Evidence Acquisition and Decision for UHR Remote Sensing Understanding — arXiv:2611.10005},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10005},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8124db13bd91; sha256 3dca7e309461cc8f4ce137a375dee3dd10a49ce725c3bb7fd7824d18973b9f43},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10005. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Ultra-high-resolution (UHR) remote sensing visual question answering (VQA) requires locating fine-grained evidence in large scenes under limited visual input budgets. Active observation addresses this challenge through selective exploration, but repeated generative judgments can make region search costly. Its decisions also concern distinct prediction targets: spatial pointer validity, evidence presence, and reasoning correctness. We propose EarthJev, a framework that separates region scoring from answer generation and uses target-specific decision signals while keeping the answering model frozen. A spatial pointer verifier uses visual and geometric cues to guide exploration or bypass search. An evidence-aware decision mechanism scores compact candidate views in batches using a lightweight head on frozen representations, without generating textual region judgments. Format-specific confidence calibration then guides selection between candidate answers generated from memory and overview presentations of the acquired evidence. Across five benchmarks, EarthJev achieves a mean accuracy of 53.06% with Qwen3.5-9B, outperforming ZoomSearch with the same answering model by 2.33 to 14.73 percentage points per benchmark while reducing mean latency from 11.30 - 1.67 seconds per question. With four additional frozen answering models, model-specific fitting of the decision modules and calibration mappings yields mean accuracy gains of 3.41 - 6.53 percentage points over the corresponding single-pass baselines. Code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.10005 — 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 2026-11-10T18:37:37.565Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).