EDGE-AWARE CONVOLUTION NEURAL NETWORK BASED SALIENT OBJECT DETECTION

Abstract

Salient object detection has received great amount of attention in recent years. In this paper, we propose a novel salient object detection algorithm, which combines the global contextual information along with the low-level edge features. First, we train an edge detection stream (EDS) based on the state-of-the-art HED model and extract hierarchical boundary information from each VGG block. Then the edge contours are served as the complementary edge-aware information and integrated with the saliency detection stream (SDS) to depict continuous boundary for salient objects. Finally, we combine pyramid pooling modules with auxiliary side output supervision to form the multi-scale Pyramid-based Supervision Module, providing multi-scale global contextual information for the saliency detection network. Compared with the previous methods, the proposed network contains more explicit edge-aware features and exploit the multi-scale global information more effectively. Experiments demonstrate the effectiveness of the proposed method, which achieves the state-of-the-art performance on five popular benchmarks.

Existing System

Pyramid-based supervision module (PSM) based on pyramid pooling module (PPM).

Proposed System

We propose a novel edge-aware fusing module (EFM) to augment the saliency detection network with explicitly supervised edge-aware features. We adopt a multi-scale pyramid-based supervision module (PSM) to exploit multi-scale global context information via varying-scale feature representation, and make saliency prediction with each auxiliary side output feature, which effectively boost the robustness of the proposed network.

Architecture

BLOCK DIAGRAM

ARCHITECTURE