Hierarchical and Interactive Refinement Network for Edge-Preserving Salient Object Detection

Abstract

Salient object detection has undergone a very rapid development with the blooming of Deep Neural Network (DNN), which is usually taken as an important preprocessing procedure in various computer vision tasks. However, the down-sampling operations, such as pooling and striding, always make the final predictions blurred at edges, which has seriously degenerated the performance of salient object detection. In this paper, we propose a simple yet effective approach, i.e., Hierarchical and Interactive Refinement Network (HIRN), to preserve the edge structures in detecting salient objects. In particular, a novel multi-stage and dual-path network structure is designed to estimate the salient edges and regions from the low-level and high-level feature maps, respectively. As a result, the predicted regions will become more accurate by enhancing the weak responses at edges, while the predicted edges will become more semantic by suppressing the false positives in background. Once the salient maps of edges and regions are obtained at the output layers, a novel edge-guided inference algorithm is introduced to further filter the resulting regions along the predicted edges.

Existing System

The traditional edge detectors, such as Canny and Laplacian.

Proposed System

We design a novel multi-stage and dual-path network to jointly learn the salient edges and regions, in which the region branch network and edge branch network can learn from each other in an interactive manner. We present a novel edge-guided inference algorithm to further filter the salient regions along the estimated edges, which is very effective and efficient to repair some small wrong predictions in salient regions.

Architecture

BLOCK DIAGRAM