EGNet: Edge Guidance Network for Salient Object Detection

By Jiaxing Zhao, Jiangjiang Liu, Deng-Ping Fan, Yang Cao, Jufeng Yang, Ming-Ming Cheng. IEEE International Conference on Computer Vision, 2019

1,078 citations recorded by the source corpus.

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/.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/115df25cc9080f0b384b3398a897767b33c42a5f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

An efficient framework for counting pedestrians crossing a line using low-cost devices: the benefits of distilling the knowledge in a neural network (2020, background): “[23] presents an edge guidance network for salient object detection.”
PraNet: Parallel Reverse Attention Network for Polyp Segmentation (2020, background): “further introduce four other metrics which are widely used in the field of object detection [7,31,8,11,37,38].”
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, methodology): “To solve the ambiguities caused by indistinguishable textures, unlike generic / salient object detection models [9,16,31,32,35,43,59,61], current COD approaches usually distill extra features from the shared context (e.”
A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection (2020, methodology): “Recent saliency detectors [14, 15] have also proved this point, in which edge knowledge is helpful to improve the saliency detection quality.”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, background): “Salient object detection (SOD) aims at detecting the objects in a scene that humans would naturally focus on [2, 9, 78].”
Kubric: A scalable dataset generator (2022, methodology): “Classical methods involve active-contour [47, 69] or graphcut [20, 104] techniques, but there also exist techniques with human-in-the-loop [72, 81, 100], and more recently deep learning variants [30, 73, 74, 105, 117].”
Weakly-Supervised Salient Object Detection via Scribble Annotations (2020, background): “Deep fully supervised saliency detection models [26, 55, 42, 50, 51, 36, 49] have been widely studied.”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, background): “, RGB SOD (Zhuge et al., 2021a; Zhang et al., 2020a; Chen et al., 2020; Zhao et al., 2019), RGB-D SOD (Zhang et al.”
Pre-Trained Image Processing Transformer (2020, methodology): “For example, the backbones of object detection models [98, 97] are often pre-trained on ImageNet classiﬁcation [18].”
Visual Saliency Transformer (2021, methodology): “Image Depth GT VST BBS-Net [16] CoNet [25] HDFNet [48] JLDCF [18] UC-Net [76] Image GT VST GateNet [84] CSF [20] LDF [69] MINet [49] ITSD [87] EGNet [82]”
Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images (2020, background): “Edge Attention Module: Several works have shown that edge information can provide useful constraints to guide feature extraction for segmentation [48]–[50].”
RGB-D salient object detection: A survey (2020, background): “progress has been made in the SOD field over the past several years [30]–[36], [36]–[44], there is still room for improvement when faced with challenging factors, such as complicated background or different lighting conditions in the scenes.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “Here, we attempt to utilize this idea for RGB-D salient object detection (SOD) [4,71], which aims at finding and segmenting the most visually outstanding object(s) [2, 72] in a scene from the RGB and depth cues.”
Kaleido-BERT: Vision-Language Pre-training on Fashion Domain (2021, methodology): “, BAS [56], EGNet [81], ICON [84] or other SOTAs in the recent paper [17]) to obtain the foreground mask and then lock (e.”
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, background): “Image GT SCRN [48] CSNet [15] F3Net [46] ITSD [59] EGNet [57] Uncertainty Ours”