Salient Object Detection: A Discriminative Regional Feature Integration Approach

TL;DR

This paper introduces a supervised learning approach for salient object detection that integrates multi-level regional features to produce accurate saliency maps, outperforming existing methods on benchmark datasets.

Contribution

It proposes a discriminative regional feature integration method using supervised learning, enhancing automatic feature selection and outperforming state-of-the-art models.

Findings

Outperforms existing methods on six benchmark datasets.

Runs as fast as most existing algorithms.

Effectively integrates high-dimensional regional features.

Abstract

Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we formulate saliency map computation as a regression problem. Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score. Saliency scores across multiple levels are finally fused to produce the saliency map. The contributions lie in two-fold. One is that we propose a discriminate regional feature integration approach for salient object detection. Compared with existing heuristic models, our proposed method is able to automatically integrate high-dimensional regional saliency features and choose discriminative ones. The other is that by investigating standard generic region properties as well as two widely studied concepts for salient object detection, i.e., regional contrast and backgroundness, our approach significantly outperforms state-of-the-art methods on six benchmark datasets. Meanwhile, we demonstrate that our method runs as fast as most existing algorithms.