An Unsupervised Game-Theoretic Approach To Saliency Detection

Keywords

Saliency; salient object detection; visual attention

Abstract

We propose a novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data. First, saliency detection problem is formulated as a non-cooperative game, hereinafter referred to as Saliency Game, in which image regions are players who choose to be 'background' or 'foreground' as their pure strategies. A payoff function is constructed by exploiting multiple cues and combining complementary features. Saliency maps are generated according to each region's strategy in the Nash equilibrium of the proposed Saliency Game. Second, we explore the complementary relationship between color and deep features and propose an iterative random walk algorithm to combine saliency maps produced by the Saliency Game using different features. Iterative random walk allows sharing information across feature spaces, and detecting objects that are otherwise very hard to detect. Extensive experiments over six challenging data sets demonstrate the superiority of our proposed unsupervised algorithm compared with several state-of-the-art supervised algorithms.

Publication Date

9-1-2018

Publication Title

IEEE Transactions on Image Processing

Volume

27

Issue

9

Number of Pages

4545-4554

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/TIP.2018.2838761

Socpus ID

85047194976 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85047194976

This document is currently not available here.

Share

COinS