Saliency detection by aggregating complementary background template with optimization framework

TL;DR

This paper introduces an unsupervised, bottom-up saliency detection method that combines multiple background templates and refinement techniques to produce more accurate and binary-like saliency maps.

Contribution

It presents a novel aggregation of complementary background templates with an optimization framework for improved unsupervised saliency detection.

Findings

Outperforms state-of-the-art methods on four datasets.

Produces more accurate and contrast-enhanced saliency maps.

Effectively refines saliency maps to be closer to binary.

Abstract

This paper proposes an unsupervised bottom-up saliency detection approach by aggregating complementary background template with refinement. Feature vectors are extracted from each superpixel to cover regional color, contrast and texture information. By using these features, a coarse detection for salient region is realized based on background template achieved by different combinations of boundary regions instead of only treating four boundaries as background. Then, by ranking the relevance of the image nodes with foreground cues extracted from the former saliency map, we obtain an improved result. Finally, smoothing operation is utilized to refine the foreground-based saliency map to improve the contrast between salient and non-salient regions until a close to binary saliency map is reached. Experimental results show that the proposed algorithm generates more accurate saliency maps and performs favorably against the state-off-the-art saliency detection methods on four publicly available datasets.