Semantic Priors for Salient Object Detection

Introduction

Salient object detection aims to detect the main objects in the given image. In this paper, we propose an approach that integrates semantic priors into the salient object detection process. The method first obtains an explicit saliency map that is refined by the explicit semantic priors learned from data. Then an implicit saliency map is constructed using a trained model that maps the implicit semantic priors embedded into superpixel features with the saliency values. Next, the fusion saliency map is computed by adaptively fusing both the explicit and implicit semantic maps. The final saliency map is eventually computed via the post-processing refinement step. Experimental results have demonstrated the effectiveness of the proposed method; particularly, it achieves competitive performance with the state-ofthe-art baselines on three challenging datasets, namely, ECSSD, HKUIS, and iCoSeg.

Overview

The flowchart of the Semantic Priors (SP) based salient object detection framework with Fully Convolutional Network used as the semantic parser: semantic scores from the semantic parser, the explicit map computation, the implicit map computation, adaptive saliency fusion, and post-processing step (Section III-E).

Publication

[1] Tam V. Nguyen, Khanh Nguyen, Thanh-Toan Do. Semantic Prior Analysis for Salient Object Detection. IEEE Trans. Image Processing 28(6): 3130-3141 (2019)

[2] Tam V. Nguyen, Luoqi Liu. Salient Object Detection with Semantic Priors. IJCAI 2017: 4499-4505

Download

• • Results of ECSSD

  • Results of HKUIS

  • Results of iCoSeg