EGNet:Edge Guidance Network for Salient Object Detection

TL;DR

EGNet introduces an edge guidance network that effectively combines edge and object information to improve the accuracy of salient object detection, especially at object boundaries, outperforming existing methods on multiple datasets.

Contribution

The paper proposes a novel single network architecture that models and fuses salient edge and object features simultaneously for improved detection accuracy.

Findings

Outperforms state-of-the-art methods on six datasets

Accurately locates object boundaries using edge guidance

No pre- or post-processing required

Abstract

Fully convolutional neural networks (FCNs) have shown their advantages in the salient object detection task. However, most existing FCNs-based methods still suffer from coarse object boundaries. In this paper, to solve this problem, we focus on the complementarity between salient edge information and salient object information. Accordingly, we present an edge guidance network (EGNet) for salient object detection with three steps to simultaneously model these two kinds of complementary information in a single network. In the first step, we extract the salient object features by a progressive fusion way. In the second step, we integrate the local edge information and global location information to obtain the salient edge features. Finally, to sufficiently leverage these complementary features, we couple the same salient edge features with salient object features at various resolutions. Benefiting from the rich edge information and location information in salient edge features, the fused features can help locate salient objects, especially their boundaries more accurately. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on six widely used datasets without any pre-processing and post-processing. The source code is available at http: //mmcheng.net/egnet/.