EGNet: Edge Guidance Network for Salient Object Detection

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/.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Camouflaged Object Segmentation CAMO EGNet MAE 0.104 # 6
Weighted F-Measure 58.3 # 7
S-Measure 73.2 # 7
E-Measure 76.8 # 7
Co-Salient Object Detection CoCA EGNet S-measure 0.603 # 9
max F-measure 0.404 # 9
mean E-measure 0.622 # 8
Mean F-measure 0.391 # 8
Camouflaged Object Segmentation COD EGNet MAE 0.056 # 3
Weighted F-Measure 50.9 # 3
S-Measure 73.7 # 4
E-Measure 77.9 # 3
Co-Salient Object Detection CoSal2015 EGNet MAE 0.099 # 8
S-measure 0.818 # 8
max F-measure 0.786 # 8
max E-measure 0.843 # 8
Co-Salient Object Detection CoSOD3k EGNet S-measure 0.7619 # 8
max E-measure 0.793 # 9
max F-measure 0.702 # 9
MAE 0.119 # 8

Methods


No methods listed for this paper. Add relevant methods here