Home > Papers

 
 
Adaptive Margin of Triplet-Center Loss for Deep Metric Learning
YAO Li,ZHANG Bin *
Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876
*Correspondence author
#Submitted by
Subject:
Funding: none
Opened online:14 January 2021
Accepted by: none
Citation: YAO Li,ZHANG Bin.Adaptive Margin of Triplet-Center Loss for Deep Metric Learning[OL]. [14 January 2021] http://en.paper.edu.cn/en_releasepaper/content/4753303
 
 
In the family loss functions built on pair-based, most of them need to manually tune uniform thresholds between pairs to optimize the parameters of network. However, those hyper-parameters are fixed which is unreasonable for the reason that any two classes have different similarity. What’s more, it has to cost too much time and energy to tune the hyper-parameters for each task to find suitable values. Therefore, this paper proposes a novel loss named adaptive margin of triplet-center loss (AMTCL), which can learn a specific margin for a center of each class, while keep inter-class separateness, enhance the discriminative power of features and lighten our burden. Finally, the proposed AMTCL obtains state-of-the-art performance on four image retrieval benchmarks. Without whistle and blow, the proposed loss only need a few codes can be easily implemented in current network.
Keywords:Deep metric learning, adaptive margin, novel loss, triplet-center
 
 
 

For this paper

  • PDF (0B)
  • ● Revision 0   
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags

Add yours

Related Papers

Statistics

PDF Downloaded 12
Bookmarked 0
Recommend 0
Comments Array
Submit your papers