Learning graph affinities for spectral graph-based salient object detection

作者：

Highlights：

• We propose a method for learning graph affinities for salient object detection.

• We employ CKNs with a global inference layer EQCUT for salient object detection.

• We provide backpropagation rules of both CKN and EQCUT for parameter learning.

• The proposed system is trained end-to-end for performance enhancement.

摘要

•We propose a method for learning graph affinities for salient object detection.•We employ CKNs with a global inference layer EQCUT for salient object detection.•We provide backpropagation rules of both CKN and EQCUT for parameter learning.•The proposed system is trained end-to-end for performance enhancement.

论文关键词：Salient object detection,Graph affinities,Spectral graph theory

论文评审过程：Received 27 April 2016, Revised 7 November 2016, Accepted 8 November 2016, Available online 12 November 2016, Version of Record 20 November 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.11.005