MicrosoftAsia-Semantics-Aligned Representation Learning for Person Re-identification---论文阅读笔记和工程实现总结原理流程摘要什么是纹理图像呢？为什么要用纹理图像？如何做的Pseudo Groundtruth Texture Images Generation?什么是语义对不齐(Semantic Misalignment)？AlignmentOur workRelated Work3. The Semantic
摘要In this paper, we propose a framework that drives the reID network to learn semantics-alignedfeature representation through delicate supervision designs提出了一个框架，一个驱动reID 网络学习语义对齐的feature represention through 精细的监督设计。学到的特征，在本质上就是语义对齐的意思。...
