A Bi-Directional Message Passing Model for Salient Object Detection

By Lu Zhang, Ju Dai, Huchuan Lu, You He, G. Wang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

448 citations recorded by the source corpus.

Recent progress on salient object detection is beneficial from Fully Convolutional Neural Network (FCN). The saliency cues contained in multi-level convolutional features are complementary for detecting salient objects. How to integrate multi-level features becomes an open problem in saliency detection. In this paper, we propose a novel bi-directional message passing model to integrate multi-level features for salient object detection. At first, we adopt a Multi-scale Context-aware Feature Extraction Module (MCFEM) for multi-level feature maps to capture rich context information. Then a bi-directional structure is designed to pass messages between multi-level features, and a gate function is exploited to control the message passing rate. We use the features after message passing, which simultaneously encode semantic information and spatial details, to predict saliency maps. Finally, the predicted results are efficiently combined to generate the final saliency map. Quantitative and qualitative experiments on five benchmark datasets demonstrate that our proposed model performs favorably against the state-of-the-art methods under different evaluation metrics.

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

View Paper: https://www.semanticscholar.org/paper/5d30c05436f5b101694ac7815b2dbec1a725d5f9

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

Pyramid Feature Attention Network for Saliency Detection (2019, methodology): “Some methods adopted certain valid strategies, such as gate function[42] and progressive attention[45], but those methods select features in a certain direction and ignore the differences between high-level and low-level features.”
A Simple Pooling-Based Design for Real-Time Salient Object Detection (2019, methodology): “[43] used a bi-directional structure to pass messages between multi-level features extracted by CNNs for better predicting saliency maps.”
Global Context-Aware Progressive Aggregation Network for Salient Object Detection (2020, methodology): “For further enhance the saliency map, several recent works (Hou et al. 2017; Zhang et al. 2017; Deng et al. 2018; Hu et al. 2018; Li et al. 2018; Zhang et al. 2018a; 2018b) integrate features in multiple layers of CNN to exploit the context information at different semantic levels.”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “And some works [67,12] also show its effectiveness in saliency detection.”
U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection (2020, methodology): “(BMPM) [50] propose to integrate features from shallow and deep layers by a controlled bi-directional passing strategy.”
Beyond Brightening Low-light Images (2021, methodology): “By taking the recurrent thought into the task, this issue is mitigated (Zhang et al. 2018).”
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (2019, methodology): “In addition, we re-train three salient object detection models for shadow detection: NLDF [25], DSS [9], BMPM [41].”
Context-aware Cross-level Fusion Network for Camouflaged Object Detection (2021, methodology): “In the field of salient object detection, [Zhang et al., 2018] utilized a multi-scale context-aware feature extraction module to allow multi-level feature maps to obtain rich context information.”
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (2019, methodology): “In [35], the work extracts context-aware multi-level features and then utilizes a bidirectional gated structure to pass messages between them.”
Multi-Scale Interactive Network for Salient Object Detection (2020, methodology): “(a, e) FCN [22]; (b) Amulet [51]; (c) BMPM [48]; (d) AIMs (Sec.”
BASNet: Boundary-Aware Salient Object Detection (2019, methodology): “Zhang et al. (BMPM) [72] proposed a controlled bi-directional passing of features between shallow and deep layers to obtain accurate predictions.”
EGNet: Edge Guidance Network for Salient Object Detection (2019, methodology): “[59] proposed a bi-directional message-passing model to integrate multi-level features for salient object detection.”
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].”
F3Net: Fusion, Feedback and Focus for Salient Object Detection (2019, methodology): “(Zhang et al. 2018a) designed a bi-directional message passing model for better feature selection and integration.”
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection (2020, methodology): “We compare our model with 16 existing saliency detection models, including 10 nearly real-time models, such as RFCN [32], Amulet [45], UCF [46], NLDF [24], CKT [18], BMP [44], PCA [22], PAGE [35], DSS [12], EGNet [48] and 6 real-time models, such as RA [3], AFNet [8], BASNet [26], CPD [37], PoolNet ”