Salient Object Detection via Augmented Hypotheses
This work addresses the problem of accurately detecting salient objects in images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackled salient object detection by proposing a method using augmented hypotheses for objectness, foreground, and compactness, resulting in a pixel-accurate saliency map that outperformed state-of-the-art approaches on MSRA-1000 and iCoSeg datasets.
In this paper, we propose using \textit{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 fore- 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.