Directional statistics-based deep metric learning for image classification and retrieval

作者：

Highlights：

• Directional statistics is introduced to the deep distance metric learning.

• A simple but effective alternative learning algorithm is proposed to learning a robust discriminative hyper-spherical feature space.

• Significant improvements on benchmark datasets for classification and retrieval tasks.

• Higher classification accuracy can be reached with shallow convolutional neural networks.

摘要

•Directional statistics is introduced to the deep distance metric learning.•A simple but effective alternative learning algorithm is proposed to learning a robust discriminative hyper-spherical feature space.•Significant improvements on benchmark datasets for classification and retrieval tasks.•Higher classification accuracy can be reached with shallow convolutional neural networks.

论文关键词：Deep distance metric learning,Directional statistics,Image retrieval,Image similarity learning

论文评审过程：Received 18 September 2018, Revised 4 April 2019, Accepted 9 April 2019, Available online 10 April 2019, Version of Record 23 April 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.005