mlsanityData to 14 Oct 2026

ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG

arXiv 2411.07688 ↗First posted 12 Nov 2024cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Ultra High Resolution (UHR) remote sensing imagery (RSI) (e.g. 100,000 × 100,000 pixels or more) poses a significant challenge for current Remote Sensing Multimodal Large Language Models (RSMLLMs). If choose to resize the UHR image to standard input image size, the extensive spatial and contextual information that UHR images contain will be neglected. Otherwise, the original size of these images often exceeds the token limits of standard RSMLLMs, making it difficult to process the entire image and capture long-range dependencies to answer the query based on the abundant visual context. In this paper, we introduce ImageRAG for RS, a training-free framework to address the complexities of analyzing UHR remote sensing imagery. By transforming UHR remote sensing image analysis task to image's long context selection task, we design an innovative image contextual retrieval mechanism based on the Retrieval-Augmented Generation (RAG) technique, denoted as ImageRAG. ImageRAG's core innovation lies in its ability to selectively retrieve and focus on the most relevant portions of the UHR image as visual contexts that pertain to a given query. Fast path and slow path are proposed in this framework to handle this task efficiently and effectively. ImageRAG allows RSMLLMs to manage extensive context and spatial information from UHR RSI, ensuring the analysis is both accurate and efficient. Codebase will be released in https://github.com/om-ai-lab/ImageRAG

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 98 of its 129 references that are in the map. First posted on arXiv 12 Nov 2024.

Builds on

98 of 129 references.

References · 98

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  8. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  9. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  11. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
38 more
  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  7. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  8. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  9. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  10. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  11. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  12. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  13. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 723
  14. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  15. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  16. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 614
  17. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 570
  18. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  19. 2023Active Retrieval Augmented Generationcited by 516
  20. 2023V*: Guided Visual Search as a Core Mechanism in Multimodal LLMscited by 482
  21. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  22. 2024Mini-Gemini: Mining the Potential of Multi-modality Vision Language Modelscited by 365
  23. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  24. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  25. 2017Functional Map of the Worldcited by 338
  26. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 328
  27. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  28. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 313
  29. 2024LongVILA: Scaling Long-Context Visual Language Models for Long Videoscited by 309
  30. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  31. 2024MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?cited by 292
  32. 2021WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learningcited by 287
  33. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  34. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  35. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 245
  36. 2015YFCC100M: The New Data in Multimedia Researchcited by 235
  37. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  38. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213

50 most cited of 98 All 98 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 2.

6 papers.

  1. 2025When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruningcited by 35
  2. 2024Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Surveycited by 23
  3. 2025Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Searchcited by 11
  4. 2025Deep Learning-Driven Ultra-High-Definition Image Restoration: A Surveycited by 6
  5. 2026SAR-RAG: ATR Visual Question Answering by Semantic Search, Retrieval, and MLLM Generationcited by 1
  6. 2026FarmMind: Reasoning-Query-Driven Dynamic Segmentation for Farmland Remote Sensing Imagescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
  2. 2026The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding
  3. 2026UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
  4. 2024Composed Image Retrieval for Remote Sensing
  5. 2025Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model
  6. 2025XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?
  7. 2026Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?
  8. 2025Beyond Pixels: A Training-Free, Text-to-Text Framework for Remote Sensing Image Retrieval