Salient Object Detection with Semantic Priors

TL;DR

This paper introduces a novel salient object detection method that integrates semantic priors, combining explicit and implicit saliency maps to produce accurate object localization, outperforming existing approaches on benchmark datasets.

Contribution

The paper presents a new framework that incorporates semantic priors into salient object detection, enhancing accuracy through explicit and implicit saliency map fusion.

Findings

Outperforms state-of-the-art methods on ECSSD and HKUIS datasets

Effectively combines semantic priors with saliency maps for improved detection

Achieves pixel-accurate saliency maps covering objects of interest

Abstract

Salient object detection has increasingly become a popular topic in cognitive and computational sciences, including computer vision and artificial intelligence research. In this paper, we propose integrating \textit{semantic priors} into the salient object detection process. Our algorithm consists of three basic steps. Firstly, the explicit saliency map is obtained based on the semantic segmentation refined by the explicit saliency priors learned from the data. Next, the implicit saliency map is computed based on a trained model which maps the implicit saliency priors embedded into regional features with the saliency values. Finally, the explicit semantic map and the implicit map are adaptively fused to form a pixel-accurate saliency map which uniformly covers the objects of interest. We further evaluate the proposed framework on two challenging datasets, namely, ECSSD and HKUIS. The extensive experimental results demonstrate that our method outperforms other state-of-the-art methods.