Hypergraph Saliency

Contextual Hypergraph Modeling for Salient Object Detection

Xi Li, Yao Li, Chunhua Shen, Anthony Dick, Anton van den Hengel

Australian Centre for Visual Technologies, Univerisity of Adelaide, Australia

Abstract: Salient object detection aims to locate objects that capture human attention within images. Previous approaches often pose this as a problem of image contrast analysis. In this work, we model an image as a hypergraph that utilizes a set of hyperedges to capture the contextual properties of image pixels or regions. As a result, the problem of salient object detection becomes one of finding salient vertices and hyperedges in the hypergraph. The main advantage of hypergraph modeling is that it takes into account each pixel’s (or region’s) affinity with its neighborhood as well as its separation from image background. Furthermore, we propose an alternative approach based on center-versus-surround contextual contrast analysis, which performs salient object detection by optimizing a cost-sensitive support vector machine (SVM) objective function. Experimental results on four challenging datasets demonstrate the effectiveness of the proposed approaches against the state-of-the-art approaches to salient object detection.

Citation: Xi Li, Yao Li, Chunhua Shen, Anthony Dick and Anton van den Hengel “Contextual Hypergraph Modeling for Salient Object Detection” International Conference on Computer Vision (ICCV), 2013. [PDF] [Supplemental material] [Poster]

Code is avaiable from Bitbucket. We also have released evalsaliency toolbox for evaluating salient object detection algorithms.

Saliency maps [Result on MSRA-1000(13.7MB)] [Result on SOD(6.1MB)] [Result on SED-100(1.1MB)] [Result on Imgsal-50(1.7MB)]

Qualitative evaluation

Examples of saliency maps (from left to right: original image, SVM saliency, hypergraph saliency):

pipeline

Quantitative evaluation

Quantitative precision-recall curves on the MSRA-1000 dataset

Quantitative precision-recall curves on the SOD dataset

Quantitative precision-recall curves on the SED-100 dataset

Quantitative precision-recall curves on the Imgsal-50 dataset

pipeline