Generalizable Person Re-identification by Domain-Invariant Mapping Network(CVPR2019)閱讀筆記
簡介 現有的域泛化方法假設源域和目標域共享相同的標籤控件，但是現有的meta學習模型假設目標域有着固定數量的類別，並且用源域中的數據去訓練， 所以他們對於reID都有侷限性，目標域中的人物類別是不同動態的 DIMN用於去學習人物圖像與其身份分類器權重向量的映射關係，使用a singel shot產生一個分類器，一旦學習好，對於目標域，每個gallery圖像將會被送入網絡中產生特殊的線性身份分類器權
相關文章
- 1. CVPR 2017 Multiple People Tracking by Lifted Multicut and Person Re-identification 閱讀筆記
- 2. 1705.IAN- The Individual Aggregation Network for Person Search 論文閱讀筆記
- 3. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 論文筆記
- 4. HashMap 閱讀筆記
- 5. LinkedHashMap 閱讀筆記
- 6. Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function 閱讀筆記
- 7. 1705.Person Re-Identification by Deep Joint Learning of Multi-Loss Classification 論文閱讀筆記
- 8. 《Knowledge Base Completion By Learning...》閱讀筆記
- 9. 【閱讀筆記】ATOM: Accurate Tracking by Overlap Maximization
- 10. 《Region Proposal by Guided Anchoring》閱讀筆記
- 更多相關文章...
- • RSS 閱讀器 - RSS 教程
- • PHP 實例 - AJAX RSS 閱讀器 - PHP教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • JDK13 GA發佈：5大特性解讀
相關標籤/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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. CVPR 2017 Multiple People Tracking by Lifted Multicut and Person Re-identification 閱讀筆記
- 2. 1705.IAN- The Individual Aggregation Network for Person Search 論文閱讀筆記
- 3. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 論文筆記
- 4. HashMap 閱讀筆記
- 5. LinkedHashMap 閱讀筆記
- 6. Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function 閱讀筆記
- 7. 1705.Person Re-Identification by Deep Joint Learning of Multi-Loss Classification 論文閱讀筆記
- 8. 《Knowledge Base Completion By Learning...》閱讀筆記
- 9. 【閱讀筆記】ATOM: Accurate Tracking by Overlap Maximization
- 10. 《Region Proposal by Guided Anchoring》閱讀筆記