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

• URL: http://arxiv.org/abs/2606.00556v1
• Date: Sat, 30 May 2026 06:13:42 GMT
• Title: Improving Visual Grounding in Remote Sensing via Cluster-Guided Refinement and Model Ensemble Voting
• Abstract summary: Visual grounding aims to locate image regions that correspond to natural language descriptions.<n>In remote sensing imagery, grounding is particularly challenging due to complex scenes, small objects, and large variations in scale.<n>We propose two grounding pipelines, that combine the complementary strengths of RemoteSAM, a visual grounding model specialized for remote sensing, and SAM3, a powerful general-purpose segmentation model.
• Score: 0.16332728502735253
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Evaluating Semantic and Spatial Guidance for Foundation Model Segmentation of Small-Scale PV in Remote Sensing Imagery [1.0993800728351737]
  Vision-language foundation models (FMs) provide a data-efficient paradigm through prompt-based semantic and spatial guidance.<n>We evaluate SAM3 for small-scale PV segmentation in RS imagery by comparing textual, geometric, and hybrid prompting.<n>Our findings establish prompting strategy as a key determinant of SAM3 adaptation, robustness, and generalization.
  arXiv  Detail & Related papers  (2026-08-11T11:16:25Z)
• More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe [52.210953881548996]
  We show that a vision-language model can achieve competitive or state-of-the-art performance at challenging remote sensing benchmarks.<n>Our model uses a single language policy that can either answer directly in text or invoke a localization tool for segmentation and grounding.<n>Our approach achieves competitive results across a broad set of benchmarks, including high-resolution, multi-temporal, multi-modal and multi-view tasks.
  arXiv  Detail & Related papers  (2026-07-17T13:25:44Z)
• Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing [0.42970700836450487]
  We present a comprehensive, multi-task empirical evaluation across remote sensing scene classification, object detection, and instance segmentation.<n>Our results demonstrate that SAM 3 avoids the overfitting commonly seen in legacy domain-adapted models.<n>It remains fundamentally constrained by sub-pixel resolution limits and overhead semantic blind spots.
  arXiv  Detail & Related papers  (2026-07-10T16:33:05Z)
• SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing [57.609801041296095]
  Vision-language models (VLMs) are emerging as powerful tools for remote sensing.<n>We enhance VLM-based visual grounding in satellite imagery by proposing a novel structured localization mechanism.
  arXiv  Detail & Related papers  (2025-12-09T18:15:43Z)
• RS-ISRefiner: Towards Better Adapting Vision Foundation Models for Interactive Segmentation of Remote Sensing Images [17.648922817109224]
  RS-ISRefiner is a novel click-based IIS framework tailored for remote sensing images.<n>It consistently outperforms state-of-the-art IIS methods in terms of segmentation accuracy, efficiency and interaction cost.
  arXiv  Detail & Related papers  (2025-11-30T04:12:43Z)
• FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensing [16.948824707021412]
  Cross-modal artificial intelligence has garnered widespread attention in recent years, achieving significant progress in the study of natural images.<n>Existing methods are mostly designed for RGB imagery, leaving a significant gap in modeling synthetic aperture radar (SAR) imagery.<n>This paper proposes FUSAR-KLIP, the first universal SAR multimodal foundational model, along with reusable data and evaluation baselines.
  arXiv  Detail & Related papers  (2025-09-28T15:03:25Z)
• TASAM: Terrain-and-Aware Segment Anything Model for Temporal-Scale Remote Sensing Segmentation [20.89385225170904]
  Segment Anything Model (SAM) has demonstrated impressive zero-shot segmentation capabilities across natural image domains.<n>We introduce TASAM, a terrain and temporally-aware extension of SAM designed specifically for high-resolution remote sensing image segmentation.
  arXiv  Detail & Related papers  (2025-09-19T09:24:24Z)
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network for Salient Object Detection in Optical Remote Sensing Images [68.33481681452675]
  We propose a graph-enhanced contextual and regional perception network (GCRPNet)<n>It builds upon the Mamba architecture to simultaneously capture long-range dependencies and enhance regional feature representation.<n>It performs adaptive patch scanning on feature maps processed via multi-scale convolutions, thereby capturing rich local region information.
  arXiv  Detail & Related papers  (2025-08-14T11:31:43Z)
• Visual and Text Prompt Segmentation: A Novel Multi-Model Framework for Remote Sensing [30.980687857037033]
  We introduce the innovative VTPSeg pipeline, utilizing the strengths of Grounding DINO, CLIP, and SAM for enhanced open-vocabulary image segmentation.<n>Our pipeline is validated by experimental and ablation study results on five popular remote sensing image segmentation datasets.
  arXiv  Detail & Related papers  (2025-03-10T23:15:57Z)
• UrbanSAM: Learning Invariance-Inspired Adapters for Segment Anything Models in Urban Construction [51.54946346023673]
  Urban morphology is inherently complex, with irregular objects of diverse shapes and varying scales.<n>The Segment Anything Model (SAM) has shown significant potential in segmenting complex scenes.<n>We propose UrbanSAM, a customized version of SAM specifically designed to analyze complex urban environments.
  arXiv  Detail & Related papers  (2025-02-21T04:25:19Z)
• RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks [11.681342476516267]
  We propose a Remote Distributed Sensing Foundation Model (RS-DFM) based on generalized information mapping and interaction. This model can realize online collaborative perception across multiple platforms and various downstream tasks. We present a dual-branch information compression module to decouple high-frequency and low-frequency feature information.
  arXiv  Detail & Related papers  (2024-06-11T07:46:47Z)
• RS-Mamba for Large Remote Sensing Image Dense Prediction [58.12667617617306]
  We propose the Remote Sensing Mamba (RSM) for dense prediction tasks in large VHR remote sensing images. RSM is specifically designed to capture the global context of remote sensing images with linear complexity. Our model achieves better efficiency and accuracy than transformer-based models on large remote sensing images.
  arXiv  Detail & Related papers  (2024-04-03T12:06:01Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.