BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network

Fan, Deng-Ping; Zhai, Yingjie; Borji, Ali; Yang, Jufeng; Shao, Ling

doi:10.1007/978-3-030-58610-2_17

Cited by 256 publications

(131 citation statements)

References 57 publications

Supporting

Mentioning

131

Contrasting

Order By: Relevance

“…For fair comparisons, we obtain the deployment codes released by authors and use the same configuration as much as possible to estimate their computational complexity. As illustrated in Table 2 , compared with the latest deep learning-based methods such as D 3 Net [ 51 ], BBS-Net [ 54 ], and UC-Net [ 55 ], our computational complexity is only one tenth or even one hundredth of theirs. Moreover, compared with the traditional-based methods such as DCMC [ 37 ], CDCP [ 18 ], and DTM [ 38 ], our model can achieve obvious higher performance in the relatively lower computational complexity combined with Table 1 .…”

Section: Experiments and Discussionmentioning

confidence: 99%

“…The literature [ 51 ] builds a new salient person (SIP) dataset with quite challenging which covers diverse real-world scenes from various viewpoints, poses, occlusion, illumination, and background. Moreover, deep learning-based RGB-D saliency detection methods [ 51 , 54 , 55 ] have developed vigorously and achieved the qualitative leap. Therefore, we look forward to extending our work to the deep learning in the future, exploring the complementarity of depth information and color information more fully, and dedicating ourselves to the studying of the saliency detection algorithm in real-world scenes.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Saliency Detection with Bilateral Absorbing Markov Chain Guided by Depth Information

Han

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

The effectiveness of depth information in saliency detection has been fully proved. However, it is still worth exploring how to utilize the depth information more efficiently. Erroneous depth information may cause detection failure, while non-salient objects may be closer to the camera which also leads to erroneously emphasis on non-salient regions. Moreover, most of the existing RGB-D saliency detection models have poor robustness when the salient object touches the image boundaries. To mitigate these problems, we propose a multi-stage saliency detection model with the bilateral absorbing Markov chain guided by depth information. The proposed model progressively extracts the saliency cues with three level (low-, mid-, and high-level) stages. First, we generate low-level saliency cues by explicitly combining color and depth information. Then, we design a bilateral absorbing Markov chain to calculate mid-level saliency maps. In mid-level, to suppress boundary touch problem, we present the background seed screening mechanism (BSSM) for improving the construction of the two-layer sparse graph and better selecting background-based absorbing nodes. Furthermore, the cross-modal multi-graph learning model (CMLM) is designed to fully explore the intrinsic complementary relationship between color and depth information. Finally, to obtain a more highlighted and homogeneous saliency map in high-level, we structure a depth-guided optimization module which combines cellular automata and suppression-enhancement function pair. This optimization module refines the saliency map in color space and depth space, respectively. Comprehensive experiments on three challenging benchmark datasets demonstrate the effectiveness of our proposed method both qualitatively and quantitatively.

show abstract

Section: Experiments and Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Saliency Detection with Bilateral Absorbing Markov Chain Guided by Depth Information

Han

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…To effectively explore the correlations between RGB images and depth maps, several methods propose a multi-scale fusion strategy [42,43,55,109,116,122,123,128]. These models can be divided into two categories.…”

Section: Multi-scale Fusionmentioning

confidence: 99%

“…BBS-Net [128] uses a bifurcated backbone strategy (BBS) to split the multi-level feature representations into teacher and student features, and develops a depth-enhanced module (DEM) to explore informative parts in depth maps from the spatial and channel views.…”

Section: Multi-scale Fusionmentioning

confidence: 99%

RGB-D salient object detection: A survey

et al. 2021

Self Cite

View full text Add to dashboard Cite

Salient object detection, which simulates human visual perception in locating the most significant object(s) in a scene, has been widely applied to various computer vision tasks. Now, the advent of depth sensors means that depth maps can easily be captured; this additional spatial information can boost the performance of salient object detection. Although various RGB-D based salient object detection models with promising performance have been proposed over the past several years, an in-depth understanding of these models and the challenges in this field remains lacking. In this paper, we provide a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail. Further, as light fields can also provide depth maps, we review salient object detection models and popular benchmark datasets from this domain too. Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection models. Finally, we discuss several challenges and open directions of RGB-D based salient object detection for future research. All collected models, benchmark datasets, datasets constructed for attribute-based evaluation, and related code are publicly available at https://github.com/taozh2017/RGBD-SODsurvey.

show abstract

“…With the increasing access to depth sensors, RGB-D SOD recently becomes a hot research topic [5][6][7][8]. Additional useful spatial information embedded in depth maps could somewhat help overcome the aforementioned challenges.…”

Section: Introductionmentioning

confidence: 99%

BTS-Net: Bi-Directional Transfer-And-Selection Network for RGB-D Salient Object Detection

Zhang

Jiang

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Depth information has been proved beneficial in RGB-D salient object detection (SOD). However, depth maps obtained often suffer from low quality and inaccuracy. Most existing RGB-D SOD models have no cross-modal interactions or only have unidirectional interactions from depth to RGB in their encoder stages, which may lead to inaccurate encoder features when facing low quality depth. To address this limitation, we propose to conduct progressive bidirectional interactions as early in the encoder stage, yielding a novel bi-directional transfer-and-selection network named BTS-Net, which adopts a set of bi-directional transfer-andselection (BTS) modules to purify features during encoding. Based on the resulting robust encoder features, we also design an effective light-weight group decoder to achieve accurate final saliency prediction. Comprehensive experiments on six widely used datasets demonstrate that BTS-Net surpasses 16 latest state-of-the-art approaches in terms of four key metrics.

show abstract

BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network

Cited by 256 publications

References 57 publications

Saliency Detection with Bilateral Absorbing Markov Chain Guided by Depth Information

Saliency Detection with Bilateral Absorbing Markov Chain Guided by Depth Information

RGB-D salient object detection: A survey

BTS-Net: Bi-Directional Transfer-And-Selection Network for RGB-D Salient Object Detection

Contact Info

Product

Resources

About