Diversity induced matrix decomposition model for salient object detection. (June 2017)

• Record Type: Journal Article
• Authors: Sun, Xiaoli; He, ZhiXiang; Xu, Chen; Zhang, Xiujun; Zou, Wenbin; Baciu, George
• Is Part Of: Pattern recognition. Volume 66(2017:Jun.)
• Page Start: 253
• Page End: 267
• Publication Date: 2017-06
• Subjects: Saliency detection -- Diversity induced term -- Matrix decompostion -- Low rank -- Group sparsity; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.01.012
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Over the past decade, salient object detection has attracted a lot of interests in computer vision. Although many models have been proposed to detect the salient object in an arbitrary image, this problem is still plagued with complex backgrounds and scattered objects. To address this issue, in this paper, we explore the information in cross features via a diversity-induced multi-view regularization under the Hilbert-Schmidt Independence Criterion (HSIC). Based on the diversity term, a new matrix decomposition based model is proposed for salient object detection. Furthermore, S 1 / 2 regularizer is introduced to constrain the background part. This regularizer will make the background much cleaner in the saliency map. A group sparsity induced norm is imposed on the salient part in order to involve the potential spatial relationships of image patches. Our method is solved through an augmented Lagrange multipliers method, and high-level priors are also integrated to boost the performance. Experiments on the four widely used datasets show that our method outperforms the state-of-the-art models. Abstract : 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.