English

Probabilistic Saliency Estimation

Computer Vision and Pattern Recognition 2017-11-16 v2

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.

Keywords

Cite

@article{arxiv.1609.03868,
  title  = {Probabilistic Saliency Estimation},
  author = {Caglar Aytekin and Alexandros Iosifidis and Moncef Gabbouj},
  journal= {arXiv preprint arXiv:1609.03868},
  year   = {2017}
}

Comments

Submitted to Pattern Recognition

R2 v1 2026-06-22T15:48:26.640Z