Probabilistic Saliency Estimation

TL;DR

This paper introduces a probabilistic framework for salient object detection that provides a closed-form solution, offers multiple interpretations, and achieves leading performance with efficient computation across large datasets.

Contribution

The paper presents a novel probabilistic approach with a closed-form solution for salient object detection, unifying various interpretations and outperforming existing methods.

Findings

Achieves state-of-the-art performance on large datasets.

Provides a closed-form global optimum for the detection problem.

Offers computational efficiency comparable to leading techniques.

Abstract

In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints in an optimization problem. We show that this problem has a closed form global optimum which estimates the salient object. We further show that along with the probabilistic framework, the proposed method also enjoys a wide range of interpretations, i.e. graph cut, diffusion maps and one-class classification. With an analysis according to these interpretations, we also find that our proposed method provides approximations to the global optimum to another criterion that integrates local/global contrast and large area saliency cues. The proposed approach achieves mostly leading performance compared to the state-of-the-art algorithms over a large set of salient object detection datasets including around 17k images for several evaluation metrics. Furthermore, the computational complexity of the proposed method is favorable/comparable to many state-of-the-art techniques.