1Saliency Detection by Multi-Task Sparsity Pursuit

Abstract—This paper addresses the problem of detecting salient areas within natural images. We shall mainly study the problem under unsupervised setting, namely saliency detection without learning from labeled images. A solution of multi-task sparsity pursuit is proposed to integrate multiple types of features for detecting saliency collaboratively. Given an image described by multiple features, its saliency map is inferred by seeking the consistently sparse elements from the joint decompositions of multiple feature matrices into pairs of low-rank and sparse matrices. The inference process is formulated as a constrained nuclear norm and ℓ2,1-norm minimization problem, which is convex and can be solved efficiently with augmented Lagrange multiplier method. Compared to previous methods, which usu-ally make use of multiple features by combining the saliency maps obtained from individual features, the proposed method seamlessly integrates multiple features to jointly produce the saliency map with a single inference step, and thus produces more accurate and reliable results. Besides the unsupervised setting, the proposed method can be also generalized to incorporate the top-down priors obtained from supervised environment. Extensive experiments well validate its superiority over other state-of-the-art methods. Index Terms—saliency detection, multi-feature modeling, multi-task learning, sparse and low-rank