Diversity induced matrix decomposition model for salient object detection

作者：

Highlights：

• A diversity induced matrix decomposition model is proposed for saliency detection.

• S1/2 regularizer is introduced to constrain the background part.

• A group sparsity induced norm is imposed on the salient part.

• We explore the cross features information via a diversity-induced regularization.

• Our performance is state-of-the-art among the unsupervised saliency models.

摘要

Highlights•A diversity induced matrix decomposition model is proposed for saliency detection.•S1/2 regularizer is introduced to constrain the background part.•A group sparsity induced norm is imposed on the salient part.•We explore the cross features information via a diversity-induced regularization.•Our performance is state-of-the-art among the unsupervised saliency models.

论文关键词：Saliency detection,Diversity induced term,Matrix decompostion,Low rank,Group sparsity

论文评审过程：Received 20 July 2016, Revised 5 January 2017, Accepted 7 January 2017, Available online 11 January 2017, Version of Record 12 March 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.01.012