深度迁移度量学习探究.pptx

Jiang Taoran Li Mingjia Deep Transfer Metric Learning Algorithms Experiments 1、Three learning methods 2、Three shortcomings Introduction 1、DTML 2、DSTML 1、Face Verification 2、Person Re-Identification Introduction 此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑 此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑此页所有文字及形状均可修改与编辑 关键词 关键词 关键词 关键词 Problems seek a single linear distance deep model similarity measure assume distributions DTML Two constraints on the outputs of all training samples at the top of the network: 1) the inter-class variations are maximized and the intra-class variations are minimized, and 2) the distribution divergence between the source domain and the target domain at the top layer of the network is minimized. DML Constructing a deep neural network to compute the representations of each sample x by passing it to multiple layers of nonlinear transformations. DML DML DMTL DMTL DMTL DMTL DMTL DSTML Face Verification Face Verification Face Verification Person Re-Identification Person Re-Identification Person Re-Identification Person Re-Identification