Metraipolis › archive › dc_2df4ff9405d9

RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQA — arXiv:2609.38072

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38072
License (as archived)
CC0-1.0
Archived
2026-10-07T18:41:42.530Z
SHA-256 of the archived text
063faef7df3daa3ffd465f38751f0324eb557114fb72104e6b4da33a146cac45
Stable URL of this page
https://metraipolis.com/documento/dc_2df4ff9405d9

How to cite

RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQA — arXiv:2609.38072 — arXiv (en), https://arxiv.org/abs/2609.38072 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2df4ff9405d9 (Metraipolis archive dc_2df4ff9405d9, sha256 063faef7df3daa3ffd465f38751f0324eb557114fb72104e6b4da33a146cac45)
BibTeX
@misc{dc2df4ff9405d9,
  title = {RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQA — arXiv:2609.38072},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38072},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2df4ff9405d9; sha256 063faef7df3daa3ffd465f38751f0324eb557114fb72104e6b4da33a146cac45},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38072. 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 models to resolve small visual evidence within extremely large images. Existing approaches typically rely on token pruning, visual search, or tool-augmented reasoning at inference time. We instead investigate whether the benefit of zoom-in visual privilege can be internalized into the model. We introduce RS-OPSD, a reliable privileged on-policy self-distillation (OPSD) framework for UHR remote sensing VQA. To provide high-quality privileged information with explicit question-relevant evidence, we construct GeoEvidence-6K, containing 6,750 VQA samples across seven task categories with evidence-region annotations, and develop Human Feedback-Guided Skill Refinement (HF-SR) for scalable annotation. To address context loss from tight crops and conflicting signals from imperfect teachers, RS-OPSD introduces Context-Preserving Visual Privilege (CPVP) and Correctness-Aligned Distillation (CAD). Without any additional visual search or tool calls at inference time, RS-OPSD achieves state-of-the-art (SOTA) performance on XLRS-Bench, MME-RealWorld-RS, and LRS-VQA, outperforming previous SOTA models of comparable scale by an average of 4.0 percentage points. Moreover, our 2B variant, RS-OPD-Lite, surpasses most 8B-scale models while achieving the fastest measured inference speed. Our Code, GeoEvidence-6K, and the model weights for RS-OPSD and RS-OPD-Lite are publicly available.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.38072 — 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 2026-10-07T18:04:24.933Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).