An Unsupervised Game-Theoretic Approach to Saliency Detection

DOI10.1109/TIP.2018.2838761MaRDI QIDQ4617467zbMATH OpenOpenAlexWikidataFDO

Authors Yu Zeng, Mengyang Feng, Hu-Chuan Lu, Gang Yang, Ali Borji

Publication date 6 February 2019

Published in IEEE Transactions on Image Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1708.02476

Mathematics Subject Classification ID

Applications of game theory (91A80) Detection theory in information and communication theory (94A13)

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 6 challenging datasets demonstrate the superiority of our proposed unsupervised algorithm compared to several state of the art supervised algorithms.

Recommendations

• Saliency detection via a graph based diffusion model
• Nonlocal variational model for saliency detection
• Saliency Detection by Multitask Sparsity Pursuit

This page was built for publication: An Unsupervised Game-Theoretic Approach to Saliency Detection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4617467)