Saliency Detection via Graph-Based Manifold Ranking

TLDR

Existing bottom‑up saliency methods mainly rely on contrast, with few focusing on background segmentation. The study proposes to use both foreground and background cues rather than contrast alone. The authors model the image as a closed‑loop graph of super‑pixels, rank nodes via graph‑based manifold ranking against foreground and background queries, and compute saliency from node relevance in a two‑stage scheme. Experimental results on two large benchmark databases show the method outperforms state‑of‑the‑art in accuracy and speed, and a new challenging benchmark of 5,172 images is released.

Abstract

Most existing bottom-up methods measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of considering the contrast between the salient objects and their surrounding regions, we consider both foreground and background cues in a different way. We rank the similarity of the image elements (pixels or regions) with foreground cues or background cues via graph-based manifold ranking. The saliency of the image elements is defined based on their relevances to the given seeds or queries. We represent the image as a close-loop graph with super pixels as nodes. These nodes are ranked based on the similarity to background and foreground queries, based on affinity matrices. Saliency detection is carried out in a two-stage scheme to extract background regions and foreground salient objects efficiently. Experimental results on two large benchmark databases demonstrate the proposed method performs well when against the state-of-the-art methods in terms of accuracy and speed. We also create a more difficult benchmark database containing 5,172 images to test the proposed saliency model and make this database publicly available with this paper for further studies in the saliency field.