Document Type

Conference Paper

Publication Date


Publication Source

24th International Joint Conference on Artificial Intelligence


In this paper, we propose using augmented hypotheses which consider objectness, foreground, and compactness for salient object detection. Our algorithm consists of four basic steps. First, our method generates the objectness map via objectness hypotheses. Based on the objectness map, we estimate the foreground margin and compute the corresponding foreground map which prefers the foreground objects. From the objectness map and the foreground map, the compactness map is formed to favor the compact objects. We then derive a saliency measure that produces a pixel-accurate saliency map which uniformly covers the objects of interest and consistently separates foreground and background.

We finally evaluate the proposed framework on two challenging datasets, MSRA-1000 and iCoSeg. Our extensive experimental results show that our method outperforms state-of-the-art approaches.

Inclusive pages


Document Version

Published Version


This document is provided for download in compliance with the publisher's policy on self-archiving. Permission documentation is on file.


Association for the Advancement of Artificial Intelligence

Place of Publication

Buenos Aires, Argentina