mlsanityData to 7 Oct 2026

MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation

arXiv 2607.06552 ↗First posted 7 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Infrared remote-sensing imagery captures intensity structure, object-background contrast, and illumination-invariant cues often invisible in RGB imagery. Yet, most remote-sensing vision-language resources and models focus on visible-band semantics, leaving infrared vision-language understanding underexplored. We introduce MonoIR-RS, a large-scale infrared remote-sensing vision-language dataset and benchmark that couples IR-aware data construction with CLIP-style contrastive adaptation and VLM instruction tuning. Built from the same source pool and split as FusionRS, MonoIR-RS retains the infrared image as the model-facing modality, yielding 600,000 synthesized infrared images and 59,032 retained IR-aware caption records. The model experiments use this retained language-supervision subset, whose captions rewrite supervision around grayscale structure and infrared-style contrast instead of RGB appearance. We show that the synthesized infrared imagery is markedly closer to real thermal imagery than a grayscale conversion on the AVIID benchmark. We fine-tune five CLIP backbones and six VLM backbones, and calibrate them against zero-shot behavior: IR-aware adaptation lifts CLIP mean recall by up to 12.8 points and drives VLM captioning IR-cue coverage to 100% while reducing residual RGB-color leakage to near zero. By isolating the infrared modality from RGB-IR dual-modal learning, MonoIR-RS offers a controlled, reproducible testbed for aligning infrared remote-sensing evidence with language.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

27 of 36 references.

References · 27

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  2. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 791
  3. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 357
  4. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 320
  5. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 313
  6. 2021LLVIP: A Visible-infrared Paired Dataset for Low-light Visioncited by 229
  7. 2023SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagerycited by 202
  8. 2017Exploring Models and Data for Remote Sensing Image Caption Generationcited by 195
  9. 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Tokencited by 164
  10. 2020Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learningcited by 150
  11. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensingcited by 150
  12. 2023SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensingcited by 123
15 more
  1. 2024VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysiscited by 84
  2. 2024EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialoguescited by 81
  3. 2022Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrievalcited by 77
  4. 2024AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalitiescited by 73
  5. 2023Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignmentcited by 71
  6. 2024GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Taskscited by 50
  7. 2024LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steeringcited by 50
  8. 2024Boosting Vision-Language Models with Transductioncited by 36
  9. 2025When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruningcited by 35
  10. 2023Domain Prompt Learning with Quaternion Networkscited by 17
  11. 2025DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understandingcited by 16
  12. 2024What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insightscited by 13
  13. 2025Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuningcited by 12
  14. 2025IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmarkcited by 11
  15. 2026FusionRS: A Large-Scale RGB-Infrared-Style Remote Sensing Dataset for Cross-Modal Vision-Language Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment
  2. 2026Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data
  3. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model
  4. 2025A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs
  5. 2026SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding
  6. 2025Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
  7. 2025Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models
  8. 2025Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives