Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
通过文本语义增强视觉表示:基于文本语义的原型用于异构联邦学习
机构 * State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China(虚拟现实技术与系统国家重点实验室,计算机科学与工程学院,北京航空航天大学,北京,中国) ; Zhongguancun Laboratory, Beijing, China(中关村实验室,北京,中国) ; Center for AI Business Innovation, Department of Management Science and Systems, School of Management, University at Buffalo, USA(人工智能商业创新中心,管理科学与系统系,管理学院,布法罗大学,美国)
AI总结 本文提出FedTSP,利用预训练语言模型构建语义丰富的原型,以解决异构联邦学习中的数据异质性问题,提升模型收敛速度和泛化能力。
Comments Accepted by CVPR 2026 (Highlight)