mlsanityData to 7 Oct 2026

VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis

arXiv 2403.20213 ↗First posted 29 Mar 2024cs.CVcited by 84

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly understand remote sensing images and perform diverse remote sensing tasks. Moreover, different from existing remote sensing instruction datasets that only include factual questions, HnstD contains additional deceptive questions stemming from the non-existence of objects. This feature prevents VHM from producing affirmative answers to nonsense queries, thereby ensuring its honesty. In our experiments, VHM significantly outperforms various vision language models on common tasks of scene classification, visual question answering, and visual grounding. Additionally, VHM achieves competent performance on several unexplored tasks, such as building vectorizing, multi-label classification and honest question answering. We will release the code, data and model weights at https://github.com/opendatalab/VHM .

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 14 of its 49 references that are in the map. First posted on arXiv 29 Mar 2024.

Builds on

14 of 49 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model4 Feb
  2. 2024Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data31 Jan
  3. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model18 Jan
  4. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark28 Jul
  5. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing20 Jun

Other references · 9

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  2. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  3. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  4. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  5. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  6. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  7. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
  8. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
  9. 2022METER-ML: A Multi-Sensor Earth Observation Benchmark for Automated Methane Source Mappingcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 30; 2026: 44.

84 papers.

Sort:

By area:

  1. 2024SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understandingcited by 101
  2. 2024EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialoguescited by 81
  3. 2025GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensingcited by 55
  4. 2024GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Groundingcited by 46
  5. 2025GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolutioncited by 41
  6. 2025SegEarth-R1: Geospatial Pixel Reasoning via Large Language Modelcited by 40
  7. 2024Towards Vision-Language Geo-Foundation Model: A Surveycited by 36
  8. 2024RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Expertscited by 29
  9. 2024LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretationcited by 25
  10. 2024Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Surveycited by 22
  11. 2025Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuningcited by 19
  12. 2025Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectivescited by 18
38 more
  1. 2025EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLMcited by 18
  2. 2026AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discoverycited by 17
  3. 2025REOBench: Benchmarking Robustness of Earth Observation Foundation Modelscited by 13
  4. 2025GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenescited by 13
  5. 2026Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodalitycited by 12
  6. 2025EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Promptingcited by 11
  7. 2025A Benchmark for Ultra-High-Resolution Remote Sensing MLLMscited by 11
  8. 2025Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Modelscited by 10
  9. 2025SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Imagescited by 10
  10. 2024RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understandingcited by 9
  11. 2026GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagerycited by 9
  12. 2025InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognitioncited by 8
  13. 2025OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligencecited by 7
  14. 2025GTR-CoT: Graph Traversal as Visual Chain of Thought for Molecular Structure Recognitioncited by 7
  15. 2025BTCChat: Advancing Remote Sensing Bi-temporal Change Captioning with Multimodal Large Language Modelcited by 7
  16. 2025Visual Instruction Pretraining for Domain-Specific Foundation Modelscited by 7
  17. 2026RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMscited by 7
  18. 2024ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAGcited by 6
  19. 2025GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensingcited by 6
  20. 2025SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Expertscited by 6
  21. 2026VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensingcited by 6
  22. 2026GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensingcited by 6
  23. 2025DescribeEarth: Describe Anything for Remote Sensing Imagescited by 5
  24. 2026GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristicscited by 5
  25. 2025DGTRSD & DGTRS-CLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision Language Foundation Model for Alignmentcited by 4
  26. 2026DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Modelscited by 4
  27. 2025Co-Training Vision Language Models for Remote Sensing Multi-task Learningcited by 3
  28. 2025GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Groundingcited by 3
  29. 2025FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensingcited by 3
  30. 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Taskscited by 3
  31. 2026Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Taskscited by 3
  32. 2025Remote Sensing Large Vision-Language Model: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modelingcited by 2
  33. 2025FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensingcited by 2
  34. 2026GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learningcited by 2
  35. 2026OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMscited by 2
  36. 2024Advancements in Visual Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement Techniquescited by 1
  37. 2025Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challengescited by 1
  38. 2025GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understandingcited by 1

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
  2. 2024Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotations
  3. 2024RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering
  4. 2025A Vision Centric Remote Sensing Benchmark
  5. 2026RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation
  6. 2023Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
  7. 2025A Benchmark for Multi-Lingual Vision-Language Learning in Remote Sensing Image Captioning
  8. 2025RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering