## 【论文推荐】最新五篇度量学习相关论文—无标签、三维姿态估计、主动度量学习、深度度量学习、层次度量学习与匹配

2018 年 4 月 5 日 专知 专知内容组

【导读】专知内容组整理了最近五篇度量学习（Metric Learning ）相关文章，为大家进行介绍，欢迎查看!

1.Mining on Manifolds: Metric Learning without Labels（对流形的挖掘:无标签的度量学习）

http://www.zhuanzhi.ai/document/25946ca9254d8330f059f75123fd100f

2.3D Pose Estimation and 3D Model Retrieval for Objects in the Wild（对自然场景下物体的三维姿态估计和三维模型检索）

http://www.zhuanzhi.ai/document/9b1f4cdd2edfcaa33b7528dc7d1fa094

3.Active Metric Learning for Supervised Classification（基于主动度量学习的监督分类

http://www.zhuanzhi.ai/document/9ba8b6a6fd182e5e787fe7ab69bd5705

4.Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval（基于方向统计的深度度量学习的图像分类和检索

http://www.zhuanzhi.ai/document/4413c2a473c060dfbf2905ea4c4615d1

5.Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences（基于层次度量学习与匹配的二维和三维几何对应

http://www.zhuanzhi.ai/document/54c5880b9c2b796588fcfda50029d483

-END-

### 相关内容

In this work we present a novel unsupervised framework for hard training example mining. The only input to the method is a collection of images relevant to the target application and a meaningful initial representation, provided e.g. by pre-trained CNN. Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds. Both types of examples are revealed by disagreements between Euclidean and manifold similarities. The discovered examples can be used in training with any discriminative loss. The method is applied to unsupervised fine-tuning of pre-trained networks for fine-grained classification and particular object retrieval. Our models are on par or are outperforming prior models that are fully or partially supervised.

Bowen Shi,Ming Sun,Krishna C. Puvvada,Chieh-Chi Kao,Spyros Matsoukas,Chao Wang
16+阅读 · 2020年2月21日
Shaolei Wang,Wanxiang Che,Qi Liu,Pengda Qin,Ting Liu,William Yang Wang
4+阅读 · 2019年8月15日
4+阅读 · 2018年7月10日
Rohit Girdhar,Georgia Gkioxari,Lorenzo Torresani,Manohar Paluri,Du Tran
5+阅读 · 2018年5月2日
Yiluan Guo,Ngai-Man Cheung
4+阅读 · 2018年4月2日
Alexander Grabner,Peter M. Roth,Vincent Lepetit
7+阅读 · 2018年3月30日
Ahmet Iscen,Giorgos Tolias,Yannis Avrithis,Ondrej Chum
6+阅读 · 2018年3月29日
Wentong Liao,Michael Ying Yang,Ni Zhan,Bodo Rosenhahn
3+阅读 · 2018年2月9日
Aljoša Ošep,Paul Voigtlaender,Jonathon Luiten,Stefan Breuers,Bastian Leibe
3+阅读 · 2017年12月23日
Top