arXiv 2607.065522026-07-08cs.CV

MonoIR-RS：基于CLIP和VLM适配的红外遥感视觉语言学习

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

China University of Petroleum-Beijing at Karamay（中国石油大学（北京）克拉玛依校区）；Guizhou University（贵州大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Shanghai Jiao Tong University（上海交通大学）

Jiaju Han, Ma Yaqi, Yahui Chai, Xuemeng Sun, Xin Li, Qike Zhang, Yingying Zhao, Xiang Chen, Luwei Yang, Chengyin Hu, Jiahuan Long

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

研究针对红外视觉语言理解未充分探索的问题，提出MonoIR-RS数据集及基准，结合多种方法构建并微调模型，提升红外遥感视觉语言学习性能，为红外与语言对齐提供可控测试平台。

摘要：

红外遥感图像能捕捉强度结构、物体与背景对比度及光照不变线索，而多数遥感视觉语言资源和模型聚焦于可见光带语义，红外视觉语言理解未被充分探索。本文介绍MonoIR-RS，一个大规模红外遥感视觉语言数据集和基准，它将红外感知数据构建与CLIP风格对比适配及VLM指令调整相结合。实验表明合成红外图像比灰度转换更接近真实热图像，微调多个骨干模型可提升性能，为红外遥感证据与语言对齐提供可控、可重复测试平台。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。