Hierarchical learning of multi-task sparse metrics for large-scale image classification

作者：

Highlights：

• An enhanced hierarchical visual tree is constructed to organize large numbers of image categories and automatically identify the inter-related tasks for multi-task sparse metric learning.

• A new objective function is define for multi-task sparse metric learning.

• A top-down approach is developed for supporting hierarchical learning of a tree of multi-task sparse metrics over the enhanced visual tree.

摘要

•An enhanced hierarchical visual tree is constructed to organize large numbers of image categories and automatically identify the inter-related tasks for multi-task sparse metric learning.•A new objective function is define for multi-task sparse metric learning.•A top-down approach is developed for supporting hierarchical learning of a tree of multi-task sparse metrics over the enhanced visual tree.

论文关键词：Hierarchical multi-task sparse metric learning,Visual tree,Large-scale image classification

论文评审过程：Received 20 July 2016, Revised 18 December 2016, Accepted 24 January 2017, Available online 3 February 2017, Version of Record 13 February 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.01.029