Papers › EGNet: Edge Guidance Network for Salient Object Detection

EGNet: Edge Guidance Network for Salient Object Detection

1 Oct 2019ICCV 2019 10archive 2025-07-28

Jia-Xing Zhao, Jiang-Jiang Liu, Deng-Ping Fan, Yang Cao, Jufeng Yang, Ming-Ming Cheng

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/.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

dagshub.com/Bharat-mtr/EGNet Syntology: not harvested report
2023-MindSpore-4/Code3 mindsporeSyntology: not harvested report
JXingZhao/EGNet pytorchSyntology: not harvested report
code-implementation1/Code3 mindsporeSyntology: not harvested report
jiean001/models_m mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HyperText: Endowing FastText with Hyperbolic Geometry (arXiv:2010.16143; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/Egnet mindsporeSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Camouflaged Object SegmentationCo-Salient Object DetectionObjectObject DetectionRGB Salient Object DetectionSalient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camouflaged Object Segmentation CAMO EGNet MAE 0.104 #12 of 14 Archive leaderboard report
Camouflaged Object Segmentation CAMO EGNet S-Measure 0.732 #12 of 14 Archive leaderboard report
Camouflaged Object Segmentation CAMO EGNet Weighted F-Measure 0.583 #12 of 14 Archive leaderboard report
Camouflaged Object Segmentation COD EGNet MAE 0.056 #10 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD EGNet S-Measure 0.737 #10 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD EGNet Weighted F-Measure 0.509 #10 of 12 Archive leaderboard report
Camouflaged Object Segmentation PCOD_1200 EGNet S-Measure 0.861 #12 of 16 Archive leaderboard report
Co-Salient Object Detection CoCA EGNet Mean F-measure 0.391 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA EGNet S-measure 0.603 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA EGNet max F-measure 0.404 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA EGNet mean E-measure 0.622 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k EGNet MAE 0.119 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k EGNet S-measure 0.7619 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k EGNet max E-measure 0.793 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k EGNet max F-measure 0.702 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 EGNet MAE 0.099 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 EGNet S-measure 0.818 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 EGNet max E-measure 0.843 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 EGNet max F-measure 0.786 #9 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections