MBTI: A Multi-Branch Efficient Fine-Tuning Framework for Hyperspectral Image Classification with Foundation Models
MBTI:一种用于基于基础模型的高光谱图像分类的多分支高效微调框架
机构 * School of Computer Science, Wuhan University(武汉大学计算机科学学院) ; State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University(武汉大学测绘遥感信息工程国家重点实验室) ; China Petroleum Pipeline Engineering Corporation(中国石油管道局工程有限公司) ; Hebei Key Laboratory of Underground Energy Storage Technology(河北省地下储能技术重点实验室) ; No. 7 Oil Production Plant, Changqing Oilfield Branch, PetroChina Company Limited(中国石油天然气股份有限公司长庆油田分公司第七采油厂) ; Faculty of Electrical Engineering and Computer Science, Ningbo University(宁波大学电气工程与计算机科学学院) ; College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院) ; School of Aerospace Information, Space Engineering University(航天工程大学航天信息学院) ; Key Laboratory of Intelligent Processing and Applicati(智能处理与应用重点实验室)
专题命中 指令微调 :foundation model(title,abstract)
AI总结 针对高光谱基础模型因传感器光谱带配置差异难以直接转移用于HSI分类的问题,提出MBTI框架,通过多分支预处理、LoRA模块及注意力融合模块,在保留光谱信息同时适应下游任务,实验证明其性能优越且可训练参数少。
Comments The code will be available at https://github.com/Azhenmiddleblock/MBTI/tree/main