DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection

By Nian Liu, Junwei Han. 2016

751 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Why Should We Add Early Exits to Neural Networks? (2020, methodology): “Apart from Inception, similar approaches have been successfully applied to, among others, face recognition [61], object detection [14], image segmentation [15], pose estimation [25], saliency detection [41], metric learning [71], visual attention prediction [69], and super resolution [34, 65].”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, methodology): “• DHSNet [37] reﬁnes the coarse saliency map by gradually combining shallower features using recurrent layers, where all the intermediate maps are supervised by the ground truth saliency maps [100].”
A Simple Pooling-Based Design for Real-Time Salient Object Detection (2019, methodology): “[23] proposed a two-stage network which produces coarse saliency maps first and then integrates local context information to refine them recurrently and hierarchically.”
Anabranch network for camouflaged object segmentation (2019, methodology): “DHS and WSS reduce accuracy while DSS and SRM slightly increase accuracy (see Table 6).”
RGB-D Object-to-CAD Retrieval (2018, methodology): “We use DHSNet [LH16] to generate a saliency map of a view sequence, The ﬁnal label of an RGB-D query object is determined by the voting scheme from the prediction scores of all view sequences generated from the object using our proposed adaptive weight estimation.”
Deeply Supervised Salient Object Detection with Short Connections (2016, methodology): “We compare the proposed approach with 7 recent CNNbased methods, including MDF [47], DS [60], DCL [35], ELD [50], MC [49], RFCN [51], and DHS [36].”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, background): “[39] designed a two-stage network, in which a coarse downscaled prediction map is produced and refined in a hierarchical and progressive manner by another network.”
EGNet: Edge Guidance Network for Salient Object Detection (2019, methodology): “Image GT Ours PiCANet [33] PAGR [63] DGRL [52] SRM [49] UCF [62] Amulet [61] DSS [17, 18] DHS [32]”
Gaze Prediction in Dynamic 360° Immersive Videos (2018, background): “Fig 5 (c) shows that after removing RGB images or saliency maps, the performance drops, this agrees with previous work [27] that the combination of initial saliency map and RGB image leads to better saliency features.”
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, methodology): “, 2016], DHSNet [Liu and Han, 2016], Hou et al.”
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (2018, background): “Liu et al. [28] ( DHS ) designed a two-stage network, in which a coarse downscaled prediction map was produced.”
Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking (2020, result): “We also compare the results of those methods obtained with the supervised deep learning, such as LEGS [63], DCL [64], DHS [65], SRM [66], RADF [36] and RFSD [32].”
Pyramid Feature Attention Network for Saliency Detection (2019, methodology): “To be speciﬁc, (1) the proposed method not only highlights the correct salient object regions clearly, but also well suppresses the saliencies [42] 0.8508 0.0484 0.9249 0.0478 0.9200 0.0392 0.8806 0.0788 0.7740 0.0635 GRL[33] 0.8341 0.0509 0.9230 0.0446 0.9130 0.0377 0.8811 0.0799 0.7788 0.0632 PAGR”
Salient Object Detection With Pyramid Attention and Salient Edges (2019, methodology): “In the field of salient object detection, although densely connected or bottom-up/top-down network architectures [54, 14, 26] (see the scheme in Fig.”
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (2018, background): “* Corresponding author contexts and the difficulty in exploring saliency-specific prior knowledge, a large body of deep convolutional neural networks (CNNs) [11-17] have been designed for RGB-induced salient object detection and have achieved appealing performance.”
Interactive Image Segmentation via Backpropagating Refinement Scheme (2019, methodology): “In [35, 30, 29], the encoder-decoder architecture [40] is used: deep features are extracted from the encoders, and they are used to predict pixel-level segmentation or saliency labels in the decoders.”
Salient object detection: A survey (2014, background): “Liu [150] propose two subnetworks to produce a prediction map in a coarse-to-fine and global-to-local manner.”
R³Net: Recurrent Residual Refinement Network for Saliency Detection (2018, background): “More recently, several works [Liu and Han, 2016; Li and Yu, 2016; Hou et al., 2017] utilized short connections to merge multi-level features of FCNs in order to simultaneously exploit high-level semantic information and low-level detailed structures for saliency detection.”
BASNet: Boundary-Aware Salient Object Detection (2019, background): “[38] proposed a deep hierarchical saliency network which learns various global structured saliency cues first and then progressively refine the details of saliency maps.”
Review of Visual Saliency Detection With Comprehensive Information (2018, methodology): “Some hierarchical deep networks for saliency detection are proposed, such as SuperCNN [38], and DHSNet [41].”