# Improving Visual Grounding in Remote Sensing via Cluster-Guided Refinement and Model Ensemble Voting

arXiv: https://arxiv.org/abs/2606.00556 · HTML: https://mlsanity.com/paper/2606.00556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 8 references that are in the map.
- First posted on arXiv 30 May 2026.

## Builds on (most cited first, 7 of 7)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2406.12384/) (2024)
- [A Survey on Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/1603.06201/) (2016)
- [RemoteSAM: Towards Segment Anything for Earth Observation](https://mlsanity.com/paper/2505.18022/) (2025)
- [Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)](https://mlsanity.com/paper/2503.11070/) (2025)
- [EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM](https://mlsanity.com/paper/2506.01667/) (2025)

## Abstract (arXiv)

Visual grounding aims to locate image regions that correspond to natural language descriptions and is a key component of interpretable vision systems. In remote sensing imagery, grounding is particularly challenging due to complex scenes, small objects, and large variations in scale. Relying on a single model is often insufficient to address these diverse challenges. In this work, we propose two grounding pipelines, Sequential Grounding Refinement (SGR) and Cluster-Aware Grounding Refinement (CGR), that combine the complementary strengths of RemoteSAM, a visual grounding model specialized for remote sensing, and SAM3, a powerful general-purpose segmentation model. Our approach first uses RemoteSAM to obtain an initial estimate of object location, which is then refined using SAM3 to produce more accurate and spatially consistent segmentations. Additionally, we explore an ensemble strategy based on majority voting across six diverse grounding pipelines, each with distinct capabilities. This multi-model framework improves robustness and significantly enhances localization accuracy. Experimental results demonstrate that the proposed pipelines and ensemble approach outperform individual models, leading to more reliable and precise visual grounding predictions.