RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQA
cs.CV
Submitted: 2026-09-29
Updated: 2026-09-30
Comments: 16 pages, 7 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Ultra-high-resolution (UHR) remote sensing visual question answering (VQA) requires models to resolve small visual evidence within extremely large images.
Terminology
Abstract
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.
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- LoRA: Low-Rank Adaptation of Large Language Models
- GPT-4o System Card
- LLaVA-OneVision: Easy Visual Task Transfer
- WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding
- HybridFlow: A Flexible and Efficient RLHF Framework
- GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models