Learning A Combined Model Of Visual Saliency For Fixation Prediction

Keywords

bottom-up attention; eye movements; para-boosting learner; regions of interest; Saliency; scene understanding; score level fusion

Abstract

A large number of saliency models, each based on a different hypothesis, have been proposed over the past 20 years. In practice, while subscribing to one hypothesis or computational principle makes a model that performs well on some types of images, it hinders the general performance of a model on arbitrary images and large-scale data sets. One natural approach to improve overall saliency detection accuracy would then be fusing different types of models. In this paper, inspired by the success of late-fusion strategies in semantic analysis and multi-modal biometrics, we propose to fuse the state-of-the-art saliency models at the score level in a para-boosting learning fashion. First, saliency maps generated by several models are used as confidence scores. Then, these scores are fed into our para-boosting learner (i.e., support vector machine, adaptive boosting, or probability density estimator) to generate the final saliency map. In order to explore the strength of para-boosting learners, traditional transformation-based fusion strategies, such as Sum, Min, and Max, are also explored and compared in this paper. To further reduce the computation cost of fusing too many models, only a few of them are considered in the next step. Experimental results show that score-level fusion outperforms each individual model and can further reduce the performance gap between the current models and the human inter-observer model.

Publication Date

4-1-2016

Publication Title

IEEE Transactions on Image Processing

Volume

25

Issue

4

Number of Pages

1566-1579

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/TIP.2016.2522380

Socpus ID

84962598208 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84962598208

This document is currently not available here.

Share

COinS