One Shot Learning with Margin

摘要：

　　One shot learning is a task of learning from a few examples,which poses a great challenge for current machine learning algorithms.One of the most effective approaches for one shot learning is metric learning.But metric-based approaches suffer from data shortage problem in one shot scenario.To alleviate this problem,we propose one shot learning with margin.The margin is beneficial to learn a more discriminative metric space.We integrate the margin into two representative one shot learning models,prototypical networks and matching networks,to enhance their generalization ability.Experimental results on benchmark datasets show that margin effectively boosts the performance of one shot learning models.

关键词： One shot learning Metric learning Meta learning

作者: Xianchao Zhang Jinlong Nie Linlin Zong Hong Yu Wenxin Liang

作者单位: School of Software,Dalian University of Technology,Dalian 116620,China;Key Laboratory for Ubiquitous School of Software Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065

会议类型: 国际会议

会议名称: The 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (第23届亚太知识发现和数据挖掘国际会议(PAKDD2019)

会议地点: 澳门

会议语种:英文

页码: 305-317

在线出版日期: 2019-04-14（万方平台首次上网日期，不代表论文的发表时间）