Accurate RGB-D Salient Object Detection via Collaborative Learning

Ji, Wei; Li, Jingjing; Zhang, Miao; Piao, Yongri; Lu, Huchuan

doi:10.1007/978-3-030-58523-5_4

Cited by 151 publications

(89 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The utilization of RGB-D data for SOD has been extensively explored for years. Traditional methods rely on hand-crafted features [25][26][27][28], while recently, deep learning-based methods have made great progress [5][6][7][8][10][11][12][13][14][15][16][17][18][19][20][21]. Based on the scope of this paper, we divide existing deep-based models into two types according to how they extract RGB and depth features, namely: parallel independent encoders (Fig.…”

Section: Related Workmentioning

confidence: 99%

“…To demonstrate the effectiveness of the proposed method, we compare it with 16 state-of-the-art (SOTA) methods, i.e. : PCF [10], MMCI [17], CPFP [16], DMRA [11], D3Net [20], SSF [12], A2dele [18], UCNet [7], JLDCF [6], cmMS [13], CoNet [19], PGAR [14], Cas-Gnn [31], DANet [21], HDFNet [8], BBSNet [5]. Quantitative results are shown in Table 1.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

“…Additional useful spatial information embedded in depth maps could somewhat help overcome the aforementioned challenges. Although a lot of advances [9] have been made in this field by exploring cross-modal complementarity [5][6][7][8][10][11][12][13][14][15][16][17][18][19][20][21][22], we notice that existing models are still insufficient on extracting robust saliency features. As shown in Fig.…”

Section: Introductionmentioning

confidence: 96%

See 2 more Smart Citations

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

Section: Related Workmentioning

confidence: 99%

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

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

show abstract

“…Experiments are conducted on a workstation with Intel Core i7-8700 CPU, Nvidia GTX 1080Ti GPU with CUDA 10.1. We implement 930 PCA [4] 534 D3Net [21] 530 JL-DCF [23] 520 cmMS [38] 430 S2MA [14] 330 CPFP [69] 278 DMRA [49] 228 CoNet [34] 167 SSF [64] 125 ASTA [63] 123 UCNet [60] 119 DANet [70] 102 DFM-Net* 93 PGAR [15] 62 A2dele [50] 57 DFM-Net 8.5…”

Section: Implementation Detailsmentioning

confidence: 99%

“…In light of this, several efficiency-oriented RGB-D SOD models have emerged with specific considerations. For example, [34,50] adopt a depth-free inference strategy for fast speed, while depth cues are only utilized in the training phase. [15,63,70] choose to design efficient cross-modal fusion modules [70] or light depth backbones [15,63].…”

Section: Introductionmentioning

confidence: 99%

Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection

Zhang

Wang

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

RGB-D salient object detection (SOD) recently has attracted increasing research interest by benefiting conventional RGB SOD with extra depth information. However, existing RGB-D SOD models often fail to perform well in terms of both efficiency and accuracy, which hinders their potential applications on mobile devices and real-world problems. An underlying challenge is that the model accuracy usually degrades when the model is simplified to have few parameters. To tackle this dilemma and also inspired by the fact that depth quality is a key factor influencing the accuracy, we propose a novel depth quality-inspired feature manipulation (DQFM) process, which is efficient itself and can serve as a gating mechanism for filtering depth features to greatly boost the accuracy. DQFM resorts to the alignment of low-level RGB and depth features, as well as holistic attention of the depth stream to explicitly control and enhance cross-modal fusion. We embed DQFM to obtain an efficient light-weight model called DFM-Net, where we also design a tailored depth backbone and a two-stage decoder for further efficiency consideration. Extensive experimental results demonstrate that our DFM-Net achieves state-of-the-art accuracy when comparing to existing non-efficient models, and meanwhile runs at 140ms on CPU (2.2× faster than the prior fastest efficient model) with only ∼8.5Mb model size (14.9% of the prior lightest). Our code will be available at https://github.com/zwbx/DFM-Net. CCS CONCEPTS• Computing methodologies → Interest point and salient region detections.

show abstract