arXiv · cs.AI · Andre Guarnier De Mitri, Giovani Decico Lucafo, Miller Matheus Lima Anacleto Rocha, Diego Furtado Silva · 10 小时前模型评分27
CAMEL:面向超轻量视网膜基础模型的跨架构掩码嵌入学习
CAMEL: Cross-Architecture Masked Embedding Learning for Ultra-Lightweight Retinal Foundation Models
导读
研究提出跨架构知识蒸馏框架 CAMEL(Cross-Architecture Masked Embedding Learning,跨架构掩码嵌入学习),通过非对称掩码策略把大型教师基础模型的知识迁移到轻量学生模型。在四个数据集上的实验显示,CAMEL 在保持精度的同时大幅降低计算复杂度,使模型可部署于硬件受限的临床环境。
分类置信度
中 · 待人工复核
- 只有单一媒体来源,需要人工复核。
来源级别:媒体与个人
应用领域:医疗与生命科学
事件类型:研究发布
证据摘录
- “To bridge this gap, we introduce CAMEL (Cross-Architecture Masked Embedding Learning), a novel cross-architecture distillation framework that uses an asymmetric masking strategy during embedding learning to effectively transfer knowledge from massive teacher foundation models to compact, lightweight student models.”
来源:arXiv · cs.AI · arxiv.org