基于语义的小样本学习原型优化方法  

Semantic-Based Prototype Optimization Method for Few-Shot Learning

作　　者：刘媛媛[1] 邵明文[1] 张黎旭 邵浚 LIU Yuanyuan;SHAO Mingwen;ZHANG Lixu;SHAO Xun(College of Computer Science and Technology,China University of Petroleum(East China),Qingdao 266580)

机构地区：[1]中国石油大学(华东)计算机科学与技术学院,青岛266580

出　　处：《模式识别与人工智能》2025年第2期132-142,共11页Pattern Recognition and Artificial Intelligence

基　　金：国家重点研发计划项目(No.2021YFA1000102);国家自然科学基金项目(No.62376285,62272375,61673396);山东省自然科学基金项目(No.ZR2022MF260)资助。

摘　　要：语义信息可为小样本学习提供丰富的先验知识,然而,现有的小样本研究只在浅层结合图像与语义,无法充分利用语义探索类别特征,从而限制模型性能.为了缓解此问题,文中提出基于语义的小样本学习原型优化方法.首先,设计逐通道级语义提示模块,引导方法提取视觉特征,逐步优化类原型.然后,设计多模态边界损失,将视觉和语义维度上的类间相关性与损失函数结合,约束方法增强类原型的区分性.最后,通过两阶段微调,充分利用语义知识优化类原型,提高分类准确率.在4个基准数据集上的实验表明文中方法性能较优.Semantic information can provide rich prior knowledge for few-shot learning.However,existing few-shot learning studies only superficially explore the combination of images and semantics,failing to fully utilize semantics to explore class features.Consequently,the model performance is limited.To address this issue,a semantic-based prototype optimization method for few-shot learning(SBPO)is proposed.First,SBPO employs channel-wise semantic prompts to guide the model in extracting visual features while progressively optimizing class prototypes.Second,a multi-modal margin loss is designed to integrate inter-class correlations in both visual and semantic dimensions with the loss function,thereby constraining the model to enhance the distinctiveness of class prototypes.Finally,through a two-stage fine-tuning process,the model can fully leverage semantic knowledge to optimize class prototypes,thereby improving classification accuracy.Experiments on four benchmark datasets demonstrate that SBPO significantly outperforms baseline methods.

关 键 词：小样本学习 原型优化 语义知识 多模态小样本学习 提示学习 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]