摘要
针对面向弱匹配的跨媒异构迁移学习中存在的迁移学习性能不高的问题,提出了一种基于平衡异构距离的混合拉普拉斯特征映射的跨媒异构迁移学习方法.利用大量非成对数据和相对少量的成对数据蕴含的语义信息,获取不同媒体域原始特征空间到潜在公共特征空间的映射矩阵;并在跨媒异构迁移学习中,构建混合图拉普拉斯矩阵,不仅保持了同一域下样本间的流形结构,而且保持不同域下样本间的流形结构;提升训练获得的模型在跨媒异构目标域的分类预测性能.在2个公共数据集NUS-WIDE和LabelMe上进行实验,表明了在成对数据的基础上,利用大量非成对数据可以增加模型的准确率和鲁棒性.
Aiming at the low transfer learning performance in cross-media heterogeneous transfer learning oriented to semi-paired problem, a novel hybrid Laplacian eigenmap based on balanced heterogeneous distance in cross-media heterogeneous transfer learning is proposed in this paper. The proposed method takes full advantage of the abundant semantic information in the massive unpaired samples and a few paired samples to learn the mapping matrices from the original feature spaces of different media domains to the latent common feature space. Moreover, by constructing mixed graph Laplacian matrix in cross-media transfer learning, it not only maintains the manifold structure of the samples from the same media domain, but also maintains the manifold structure of the samples from different media domains, which promotes the model performance in the target media domain. Extensive experiments are conducted on two common datasets: the NUS-WIDE and LabelMe. The experimental results show that the accuracy and robustness of the model can be increased by using a large number of unpaired data and a few of paired data simultaneously.
作者
赵鹏
高浩渊
姚晟
杜奕
Zhao Peng;Gao Haoyuan;Yao Sheng;Du Yi(Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education,Anhui University,Hefei 230601;School of Computer Science and Technology,Anhui University,Hefei 230601;College of Engineering,Shanghai Polytechnic University,Shanghai 201209)
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2019年第11期1963-1972,共10页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金(61602004)
安徽省高校自然科学研究重点项目(KJ2018A0013,KJ2017A011)
安徽省自然科学基金(1908085MF188,1908085MF182)
安徽省重点研究与开发计划项目(1804d08020309)
关键词
跨媒异构迁移学习
弱匹配问题
异构距离
混合图拉普拉斯矩阵
cross-media heterogeneous transfer learning
semi-paired problem
heterogeneous distance
mixed graph Laplacian matrix
