Generalizable Person Re-identification by Domain-Invariant Mapping Network(CVPR2019)阅读笔记
简介 现有的域泛化方法假设源域和目标域共享相同的标签控件，但是现有的meta学习模型假设目标域有着固定数量的类别，并且用源域中的数据去训练， 所以他们对于reID都有局限性，目标域中的人物类别是不同动态的 DIMN用于去学习人物图像与其身份分类器权重向量的映射关系，使用a singel shot产生一个分类器，一旦学习好，对于目标域，每个gallery图像将会被送入网络中产生特殊的线性身份分类器权
相关文章
- 1. CVPR 2017 Multiple People Tracking by Lifted Multicut and Person Re-identification 阅读笔记
- 2. 1705.IAN- The Individual Aggregation Network for Person Search 论文阅读笔记
- 3. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记
- 4. HashMap 阅读笔记
- 5. LinkedHashMap 阅读笔记
- 6. Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function 阅读笔记
- 7. 1705.Person Re-Identification by Deep Joint Learning of Multi-Loss Classification 论文阅读笔记
- 8. 《Knowledge Base Completion By Learning...》阅读笔记
- 9. 【阅读笔记】ATOM: Accurate Tracking by Overlap Maximization
- 10. 《Region Proposal by Guided Anchoring》阅读笔记
- 更多相关文章...
- • RSS 阅读器 - RSS 教程
- • PHP 实例 - AJAX RSS 阅读器 - PHP教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. CVPR 2017 Multiple People Tracking by Lifted Multicut and Person Re-identification 阅读笔记
- 2. 1705.IAN- The Individual Aggregation Network for Person Search 论文阅读笔记
- 3. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记
- 4. HashMap 阅读笔记
- 5. LinkedHashMap 阅读笔记
- 6. Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function 阅读笔记
- 7. 1705.Person Re-Identification by Deep Joint Learning of Multi-Loss Classification 论文阅读笔记
- 8. 《Knowledge Base Completion By Learning...》阅读笔记
- 9. 【阅读笔记】ATOM: Accurate Tracking by Overlap Maximization
- 10. 《Region Proposal by Guided Anchoring》阅读笔记