A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner. In this paper, we propose a multi-task deep saliency model based on a fully convolutional neural network with global input (whole raw images) and global output (whole saliency maps). In principle, the proposed saliency model takes a data-driven strategy for encoding the underlying saliency prior information, and then sets up a multi-task learning scheme for exploring the intrinsic correlations between saliency detection and semantic image segmentation. Through collaborative feature learning from such two correlated tasks, the shared fully convolutional layers produce effective features for object perception. Moreover, it is capable of capturing the semantic information on salient objects across different levels using the fully convolutional layers, which investigate the feature-sharing properties of salient object detection with a great reduction of feature redundancy. Finally, we present a graph Laplacian regularized nonlinear regression model for saliency refinement. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.
Bibliographical noteFunding Information:
Manuscript received October 19, 2015; revised April 15, 2016 and June 1, 2016; accepted June 6, 2016. Date of publication June 9, 2016; date of current version June 28, 2016. This work was supported in part by the National Natural Science Foundation of China under Grant 61472353 and Grant U1509206, in part by the National Basic Research Program of China under Grant 2012CB316400 and Grant 2015CB352302, in part by the Fundamental Research Funds for the Central Universities. The work of M.-H. Yang was supported in part by the NSF CAREER Grant 1149783 and the NSF IIS Grant 1152576. The work of H. Ling was supported in part by the National Natural Science Foundation of China under Grant 61528204 and the NSF IIS Grants 1218156 and 1350521. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Nikolaos V. Boulgouris.
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design