Hierarchical Saliency Detection

TLDR

Saliency detection struggles with complex objects when small‑scale high‑contrast patterns in foreground or background degrade accuracy, a common challenge in natural images. The study proposes a multi‑layer, scale‑based approach to analyze saliency cues. A hierarchical tree model is used to optimally compute saliency values across scales, producing the final saliency map, and a new dataset was constructed to support evaluation. The method improves saliency detection on images that are difficult for traditional approaches.

Abstract

When dealing with objects with complex structures, saliency detection confronts a critical problem - namely that detection accuracy could be adversely affected if salient foreground or background in an image contains small-scale high-contrast patterns. This issue is common in natural images and forms a fundamental challenge for prior methods. We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. The final saliency map is produced in a hierarchical model. Different from varying patch sizes or downsizing images, our scale-based region handling is by finding saliency values optimally in a tree model. Our approach improves saliency detection on many images that cannot be handled well traditionally. A new dataset is also constructed.