Learning deep similarity models with focus ranking for fabric image retrieval
作者：
Highlights：
• We propose a novel focus ranking embedding method for fabric image retrieval.
• Our method can be unified in Convolutional Neural Networks for deep model learning.
• We apply focus ranking unit generation to model training and optimization.
• We build a large-scale fabric image retrieval dataset (FIRD).
• Extensive experiments demonstrate the superiority of our method.
摘要
•We propose a novel focus ranking embedding method for fabric image retrieval.•Our method can be unified in Convolutional Neural Networks for deep model learning.•We apply focus ranking unit generation to model training and optimization.•We build a large-scale fabric image retrieval dataset (FIRD).•Extensive experiments demonstrate the superiority of our method.
论文关键词：Convolutional neural network,Fabric image retrieval,Metric embedding,Focus ranking
论文评审过程：Received 29 March 2017, Revised 21 October 2017, Accepted 10 December 2017, Available online 13 December 2017, Version of Record 26 December 2017.
论文官网地址：https://doi.org/10.1016/j.imavis.2017.12.005
