VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing

• URL: http://arxiv.org/abs/2512.11490v1
• Date: Fri, 12 Dec 2025 11:39:35 GMT
• Title: VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing
• Authors: Emanuel Sánchez Aimar, Gulnaz Zhambulova, Fahad Shahbaz Khan, Yonghao Xu, Michael Felsberg,
• Abstract summary: Single-encoder vision-language model trained contrastively to embed interleaved inputs in a unified vector space.<n>VLM2GeoVec unifies scalable retrieval with region-level spatial reasoning, enabling cohesive multimodal analysis in remote sensing.
• Score: 59.73939718087177
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Satellite imagery differs fundamentally from natural images: its aerial viewpoint, very high resolution, diverse scale variations, and abundance of small objects demand both region-level spatial reasoning and holistic scene understanding. Current remote-sensing approaches remain fragmented between dual-encoder retrieval models, which excel at large-scale cross-modal search but cannot interleave modalities, and generative assistants, which support region-level interpretation but lack scalable retrieval capabilities. We propose $\textbf{VLM2GeoVec}$, an instruction-following, single-encoder vision-language model trained contrastively to embed interleaved inputs (images, text, bounding boxes, and geographic coordinates) in a unified vector space. Our single encoder interleaves all inputs into one joint embedding trained with a contrastive loss, eliminating multi-stage pipelines and task-specific modules. To evaluate its versatility, we introduce $\textbf{RSMEB}$, a novel benchmark covering key remote-sensing embedding applications: scene classification; cross-modal search; compositional retrieval; visual-question answering; visual grounding and region-level reasoning; and semantic geospatial retrieval. On RSMEB, it achieves $\textbf{26.6%}$ P@1 on region-caption retrieval (+25 pp vs. dual-encoder baselines), $\textbf{32.5%}$ P@1 on referring-expression retrieval (+19 pp), and $\textbf{17.8%}$ P@1 on semantic geo-localization retrieval (over $3\times$ prior best), while matching or exceeding specialized baselines on conventional tasks such as scene classification and cross-modal retrieval. VLM2GeoVec unifies scalable retrieval with region-level spatial reasoning, enabling cohesive multimodal analysis in remote sensing. We will publicly release the code, checkpoints, and data upon acceptance.

Related papers

• LLandMark: A Multi-Agent Framework for Landmark-Aware Multimodal Interactive Video Retrieval [0.0]
  LLandMark is a modular framework for landmark-aware multimodal video retrieval.<n>The framework features specialized agents that collaborate across four stages: query parsing and planning, landmark reasoning, multimodal retrieval, and reranked answer synthesis.<n>A key component, the Landmark Knowledge Agent, detects cultural or spatial landmarks and reformulates them into descriptive visual prompts, enhancing CLIP-based semantic matching for Vietnamese scenes.
  arXiv  Detail & Related papers  (2026-03-03T11:36:34Z)
• Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models [58.46663983451155]
  PixSearch is an end-to-end Segmenting Large Multimodal Model (LMM) that unifies region-level perception and retrieval-augmented reasoning.<n>During encoding, PixSearch emits search> tokens to trigger retrieval, selects query modalities (text, image, or region), and generates pixel-level masks that directly serve as visual queries.<n>On egocentric and entity-centric VQA benchmarks, PixSearch substantially improves factual consistency and generalization.
  arXiv  Detail & Related papers  (2026-01-27T00:46:08Z)
• A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization [49.13032757301023]
  We present a winning solution to RoboSense 2025 Track 4: Cross-Modal Drone Navigation.<n>The task retrieves the most relevant geo-referenced image from a large multi-platform corpus.<n>We train three platform experts using a progressive two-stage, hard-negative mining strategy to enhance discriminative power.
  arXiv  Detail & Related papers  (2025-10-23T07:23:47Z)
• MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval [86.35779264575154]
  Multimodal retrieval is becoming a crucial component of modern AI applications, yet its evaluation lags behind the demands of more realistic and challenging scenarios.<n>We introduce MR$2$-Bench, a reasoning-intensive benchmark for multimodal retrieval.
  arXiv  Detail & Related papers  (2025-09-30T15:09:14Z)
• OSDA: A Framework for Open-Set Discovery and Automatic Interpretation of Land-cover in Remote Sensing Imagery [10.196580289786414]
  Open-set land-cover analysis in remote sensing requires the ability to achieve fine-grained spatial localization and semantically open categorization.<n>We introduce OSDA, an integrated three-stage framework for annotation-free open-set land-cover discovery, segmentation, and description.<n>Our work provides a scalable and interpretable solution for dynamic land-cover monitoring, showing strong potential for automated cartographic updating and large-scale earth observation analysis.
  arXiv  Detail & Related papers  (2025-09-23T06:23:56Z)
• Saccadic Vision for Fine-Grained Visual Classification [10.681604440788854]
  Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features.<n>Existing part-based methods rely on complex localization networks that learn mappings from pixel to sample space.<n>We propose a two-stage process that first extracts peripheral features and generates a sample map.<n>We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations.
  arXiv  Detail & Related papers  (2025-09-19T07:03:37Z)
• Robust Cross-View Geo-Localization via Content-Viewpoint Disentanglement [21.192114177279695]
  Cross-view geo-localization (CVGL) aims to match images of the same geographic location captured from different perspectives, such as drones and satellites.<n>CVGL remains highly challenging due to significant appearance changes and spatial distortions caused by viewpoint variations.<n>We propose $textbfCVD$, a new CVGL framework that explicitly disentangles $textitcontent$ and $textitviewpoint$ factors.
  arXiv  Detail & Related papers  (2025-05-17T04:10:32Z)
• GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning [51.677086019209554]
  We propose a Generalized Structural Sparse to capture powerful relationships across modalities for pair-wise similarity learning. The distance metric delicately encapsulates two formats of diagonal and block-diagonal terms. Experiments on cross-modal and two extra uni-modal retrieval tasks have validated its superiority and flexibility.
  arXiv  Detail & Related papers  (2024-10-20T03:45:50Z)
• Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation [34.786268652516355]
  Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data. We propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning. In particular, the framework contains a Depth-guided Contextual Filter (DCF) forndata augmentation and a cross-task encoder for contextual learning.
  arXiv  Detail & Related papers  (2023-11-21T15:39:21Z)
• Hierarchical Matching and Reasoning for Multi-Query Image Retrieval [113.44470784756308]
  We propose a novel Hierarchical Matching and Reasoning Network (HMRN) for Multi-Query Image Retrieval (MQIR) It disentangles MQIR into three hierarchical semantic representations, which is responsible to capture fine-grained local details, contextual global scopes, and high-level inherent correlations. Our HMRN substantially surpasses the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-26T07:03:56Z)
• A Simple Framework for Open-Vocabulary Segmentation and Detection [85.21641508535679]
  We present OpenSeeD, a simple Open-vocabulary and Detection framework that jointly learns from different segmentation and detection datasets. We first introduce a pre-trained text encoder to encode all the visual concepts in two tasks and learn a common semantic space for them. After pre-training, our model exhibits competitive or stronger zero-shot transferability for both segmentation and detection.
  arXiv  Detail & Related papers  (2023-03-14T17:58:34Z)
• AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation [96.29533512606078]
  We present AutoPose, a novel neural architecture search(NAS) framework. It is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation.
  arXiv  Detail & Related papers  (2020-08-16T22:27:43Z)

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.