Robust object recognition via weakly supervised metric and template learning
作者: Min TanZhenfang HuBaoyuan WangJieyi ZhaoYueming Wang
作者单位: 1College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, PR China
2Microsoft Research, Redmond 98052, United States
3The University of Texas Health Science Center at Houston, Houston 77030, United States
4Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou 310027, PR China
刊名: Neurocomputing, 2016, Vol.181 , pp.96-107
来源数据库: Elsevier Journal
DOI: 10.1016/j.neucom.2015.04.123
关键词: Metric learningTemplate learningObject recognitionWeakly supervised learning
原始语种摘要: Abstract(#br)In this paper, we present a new framework for object recognition via weakly supervised metric and template learning, wherein the optimal metric and templates are jointly learned. Its advantages include high computational speed, and robustness against image noise and unbalanced training data. Specifically, considering the noise in the training data, our framework is formulated as a weakly supervised learning model in which images with higher reliability will contribute more to the training result. A latent structural SVM based W eakly S upervised M etric and T emplate L earning (WSMTL) method is designed to jointly learn the metric, the templates, and a weight vector. The weight vector is used to represent each image׳s reliability. With the learned metric and object templates,...
全文获取路径: Elsevier  (合作)
影响因子:1.634 (2012)

  • 学习 坚固性
  • recognition 识别
  • metric 米制的
  • template 模板
  • training 培养
  • object 目标
  • computational 计算的
  • robustness 坚固性
  • learn 坚固性
  • weakly 弱的
  • database 资料库