Detect Globally, Refine Locally: A Novel Approach to Saliency Detection

By Tiantian Wang, Lihe Zhang, Shuo Wang, Huchuan Lu, Gang Yang, Xiang Ruan, Ali Borji. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

391 citations recorded by the source corpus.

Effective integration of contextual information is crucial for salient object detection. To achieve this, most existing methods based on 'skip' architecture mainly focus on how to integrate hierarchical features of Convolutional Neural Networks (CNNs). They simply apply concatenation or element-wise operation to incorporate high-level semantic cues and low-level detailed information. However, this can degrade the quality of predictions because cluttered and noisy information can also be passed through. To address this problem, we proposes a global Recurrent Localization Network (RLN) which exploits contextual information by the weighted response map in order to localize salient objects more accurately. Particularly, a recurrent module is employed to progressively refine the inner structure of the CNN over multiple time steps. Moreover, to effectively recover object boundaries, we propose a local Boundary Refinement Network (BRN) to adaptively learn the local contextual information for each spatial position. The learned propagation coefficients can be used to optimally capture relations between each pixel and its neighbors. Experiments on five challenging datasets show that our approach performs favorably against all existing methods in terms of the popular evaluation metrics.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/239f8b0262622e90eb9353b101419027e69c6a50

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

Citations in the corpus

Global Context-Aware Progressive Aggregation Network for Salient Object Detection (2020, neutral): “…Amulet (Zhang et al. 2017), C2S (Li et al. 2018), RANet (Chen et al. 2018), PAGR (Zhang et al. 2018b), PiCANet-R (Liu, Han, and Yang 2018), DGRL (Wang et al. 2018), R 3 Net (Deng et al. 2018), BMPM (Zhang et al. 2018a), RADF (Hu et al. 2018), CPD-R (Wu, Su, and Huang 2019), BASNet (Qin et al.…”
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (2019, methodology): “Then fully convolutional networks (FCNs) [23] based approaches [4, 15, 22, 24, 29, 30, 31, 35, 36, 37] further boost the development of salient object detection.”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, background): “As a specific example, here we focus on salient object detection (Borji et al., 2015; Borji & Itti, 2013; Borji, 2015;Bylinskii et al., 2015;Zhanget al., 2017, 2018a, 2018b, 2018c; Wang et al., 2018; Chen & Li, 2018; Gorji & Clark, 2018; Li et al., 2018; Zeng et al., 2018; Liu et al., 2018; Tiantian”
F3Net: Fusion, Feedback and Focus for Salient Object Detection (2019, neutral): “2018), PiCA-R (Liu, Han, and Yang 2018), DGRL (Wang et al. 2018), TDBU (Wang et al.”
BASNet: Boundary-Aware Salient Object Detection (2019, methodology): “We compare our method with 15 state-of-the-art models, PiCANetR [39], BMPM [72], R3Net [6], PAGRN [76], RADF [19], DGRL [65], RAS [4], C2S [36], LFR [73], DSS [17], NLDF [41], SRM [64], Amulet [74], UCF [75], MDF [35].”
Label Decoupling Framework for Salient Object Detection (2020, methodology): “To demonstrate the effectiveness of the proposed method, 14 state-of-the-art SOD methods are introduced to compare, including BMPM [38], DGRL [28], R(3)Net [7], RAS [4], PiCA-R [21], AFNet [13], BASNet [23], CPD-R [33], EGNet-R [41], PAGE [31], TDBU [30], SCRN [34], SIBA [24] and PoolNet [20].”
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (2019, methodology): “The other is average F-measure (denoted as avgF), which is adopted in [35, 36, 42, 43].”
Weakly-Supervised Salient Object Detection via Scribble Annotations (2020, methodology): “Models Metric DGRL UCF PiCANet R3Net NLDF MSNet CPD AFNet PFAN PAGRN BASNet SBF WSI WSS MNL MSW Ours [35] [53] [21] [5] [23] [40] [41] [8] [56] [54] [26] [48] [16] [34] [52] [47]”
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].”
Shifting More Attention to Video Salient Object Detection (2019, background): “More recently, deep learning based VSOD models [31, 38, 39, 41, 67, 68, 76] have gained more attention inspired by the success of applying deep neural networks on image saliency detection [13–15,32,50,71,72,86,88–90,94].”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “And many methods aim at combining multilevel features in either the encoder [69,53,67,57,37,59] or the decoder [29,20,70,59].”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, background): “As discussed in [43,61], teacher features 5 provide discriminative semantic information that serves as strong guidance for locating salient objects, while student features carry aﬄu-ent details that are beneﬁcial for reﬁning edges.”
Deepstrip: High-Resolution Boundary Refinement (2020, background): “Recent decades have witnessed considerable effort to improve the boundary quality of an object that has been detected [41, 35, 32, 18, 37, 47, 16, 22] or segmented [11, 34, 24, 7].”
Survey on Deep Neural Networks in Speech and Vision Systems (2019, methodology): “For example, in [114], RNN is used to refine CNN feature maps by iteratively leveraging deeper contextual information than pure CNN.”
Multi-Scale Interactive Network for Salient Object Detection (2020, methodology): “2); (f) DSS [13]; (g) DGRL [34]; (h) SIMs (Sec.”
Salient Object Detection With Pyramid Attention and Salient Edges (2019, methodology): “For a fair comparison, we exclude other ResNet-based models such as [39], or the ones us-ing more training data [40].”