Deep networks for saliency detection via local estimation and global search

By Lijun Wang, Huchuan Lu, Xiang Ruan, Ming-Hsuan Yang. 2015

650 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

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

In Sensory Systems

Citations in the corpus

Recent advances in convolutional neural networks (2015, background): “[166] introduces a novel saliency detection algorithm which sequentially exploits local context and global context.”
Saliency in VR: How Do People Explore Virtual Environments? (2016, background): “Recently, advances in machine learning and particularly convolutional neuronal networks (CNNs) have fostered the convergence of top-down and bottom-up features for saliency prediction, producing more accurate models [20,34,42,59,63].”
Anabranch network for camouflaged object segmentation (2019, methodology): “To leverage the advantage of deep learning, recent methods ﬁrst conduct superpixel segmentation and then feed segmented regions into a convolutional neural network (CNN) individually to obtain saliency scores (Le and Sugimoto, 2018; Li and Yu, 2015; Wang et al., 2015).”
A Stagewise Refinement Model for Detecting Salient Objects in Images (2017, methodology): “Ours BL DCL DHS DRFI DS ELD KSR LEGS MCDL MDF RFCN Time (s) 0.07 31.73 0.41 0.04 46.21 0.12 0.57 50.90 1.54 2.27 21.55 4.72 (i) (ii) (iii) (iv) 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Precision Recall Fmeasure (i) (ii) (iii) (iv) 0.4 0.5 0.6 0.7 0.8 0.9 Precision Recall Fmeasure Figure 9.”
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup (2020, methodology): “Subsequently, other methods were introduced to obtain more precise saliency (Zhao et al., 2015; Wang et al., 2015).”
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (2018, methodology): “In LEGS [36], local information and global contrast were separately captured by two diﬀerent deep CNNs, and were then fused to generate a saliency map.”
New Contour Cue-Based Hybrid Sparse Learning for Salient Object Detection (2019, methodology): “…we denote as BMS [10], CA [52], CB [35], CGVS [53], CRF [15], DSR [20], FES [54], FT [16], GMR [30], GR [36], GS [28], HS [55], LC [56], LEGS [42], LMLC [41], LPS [57], MBS (MBS+) [45], MC [29], MNP [58], PSO [59], RC [17], SEG [60], SeR [61], SF [49], ST [62], and SVO [34], respectively.”
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, methodology): “[36] first used CNNs to predict saliency from local contexts and then adapted DNNs to use global features to refine the saliency”
Attentive Feedback Network for Boundary-Aware Salient Object Detection (2019, result): “We compared our algorithm with other 12 state-ofthe-art deep learning methods, which are LEGS [26], RFCN [28], ELD [13], DCL [16], DS [18], DHS [21], Amulet [33], DSS [10], C2SNet [17], RAS [5], DGRL [29] and PiCANet [22].”
Shallow and Deep Convolutional Networks for Saliency Prediction (2016, methodology): “proposed a different pipeline [28]: local estimation is carried out and the resulting information is used as input to obtain a global search.”
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (2019, methodology): “Early works utilize CNNs to determine whether image regions are salient or not [15, 16, 32, 44].”
Deep Saliency with Encoded Low Level Distance Map and High Level Features (2016, methodology): “[16] (f) LEGS [27] (g) DRFI [13], (h) DSR [17], (i) GMR [30], (j) HDCT [15] (k) HS [29].”
Deep Contrast Learning for Salient Object Detection (2016, methodology): “[44] adopted a deep neural network (DNNL) to learn local patch features for each centered pixel.”
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey (2018, methodology): “We selected seven models that were published in 2015 and 2016 and have released their codes or computed saliency maps: LEGS [46], DHS [20], DCL [48], ELD [47], MCDL [87], MDF [83], and RFCN [49].”
Saliency Guided Experience Packing for Replay in Continual Learning (2021, background): “Several works followed up that improved the quality of saliency maps (Zhao et al. 2015; Wang et al. 2015) and reduced the cost for saliency computation (Zhou et al.”
RGBD Salient Object Detection via Deep Fusion (2016, methodology): “2) Performance Comparison: In this section, we compare our method with four state-of-the-art methods designed for RGB images (S-CNN [41], BSCA [16], MB+ [53], and LEGS [42]) and four RGBD saliency methods designed especially for RGBD images (LMH [12], ACSD [13], GP [14], and LBE [15]).”
Learning Uncertain Convolutional Features for Accurate Saliency Detection (2017, methodology): “[44] propose two deep neural networks to integrate local estimation and global search for saliency detection.”
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings (2017, methodology): “Our baselines for the saliency estimation task include (a) the Local Estimation and Global Search (LEGS) framework [36], (b) the multi-context network [39], (c) the multiscale deep features network [21], (d) the deep contrast learning networks [22] which proposes a network structure that better expl”
Visual Tracking with Fully Convolutional Networks (2015, background): “, image classification [16, 27], object detection [8, 23, 22], and saliency detection [33, 39].”