Select, Supplement and Focus for RGB-D Saliency Detection

Zhang, Miao; Ren, Weisong; Piao, Yongri; Rong, Zhengkun; Lu, Huchuan

doi:10.1109/cvpr42600.2020.00353

Cited by 194 publications

(153 citation statements)

References 30 publications

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…To quantify the performance of different models, we conducted a comprehensive evaluation of 24 representative RGB-D based salient object detection models, including nine traditional methods: LHM [51], ACSD [56], DESM [49], GP [50], LBE [57], DCMC [36], SE [37], CDCP [84], CDB [95], and fifteen deep learning-based methods: DF [52], PCF [92], CTMF [58], CPFP [53], TANet [103], AFNet [106], MMCI [55], DMRA [54], D 3 Net [38], SSF [39], A2dele [40], S 2 MA [41], ICNet [42], JL-DCF [43], and UC-Net [44]. We report the mean values of S α and MAE across the five datasets (STERE [139], NLPR [51] , LFSD [140], DES [49], and SIP [38]) for each model in Fig.…”

Section: Overall Evaluationmentioning

confidence: 99%

“…• Comparison of deep models. Among the deep learning-based models, D 3 Net [38], JL-DCF [43], UC-Net [44], SSF [39], ICNet [42], and S 2 MA [41] obtain the best performance. Figures 6 and 7 show PR and F-measure curves for the 24 representative RGB-D based salient object detection models, for eight datasets: STERE [139], NLPR [51], LFSD [140], DES [49], SIP [38], GIT [47], SSD [85] , and NJUD [56]).…”

Section: Overall Evaluationmentioning

confidence: 99%

“…In SSF [39], a complementary interaction module (CIM) is developed to explore discriminative crossmodal complementarity and to fuse cross-modal features, where region-wise attention is introduced to supplement rich boundary information for each modality. A compensation-aware loss is used to improve the network's confidence for hard samples in unreliable depth maps.…”

Section: Overall Evaluationmentioning

confidence: 99%

“…All models are worse at salient object detection for images with complex backgrounds than simple ones. Among the representative models, JL-DCF [43], UC-Net [44], and SSF [39] achieve the three best results. The four most recent models: D 3 Net [38], S 2 MA [41], A2dele [40], and ICNet [42], obtain better performance than the other models.…”

Section: Attribute-based Evaluationmentioning

confidence: 99%

“…Despite the effectiveness of traditional methods using handcrafted features, their low-level features tend Fig. 1 RGB-D based salient object prediction on a sample image using two classical models: DCMC [36] and SE [37], and seven stateof-the-art deep models: D 3 Net [38], SSF [39], A2dele [40], S 2 MA [41], ICNet [42], JL-DCF [43], and UC-Net [44].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

RGB-D salient object detection: A survey

et al. 2021

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

Section: Overall Evaluationmentioning

confidence: 99%

Section: Overall Evaluationmentioning

confidence: 99%

Section: Overall Evaluationmentioning

confidence: 99%

Section: Attribute-based Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

RGB-D salient object detection: A survey

et al. 2021

View full text Add to dashboard Cite

show abstract

RGB-D Salient Object Detection with Cross-Modality Modulation and Selection

Cong

Piao

et al. 2020

Lecture Notes in Computer Science

Self Cite

120

View full text Add to dashboard Cite

We present an effective method to progressively integrate and refine the cross-modality complementarities for RGB-D salient object detection (SOD). The proposed network mainly solves two challenging issues: 1) how to effectively integrate the complementary information from RGB image and its corresponding depth map, and 2) how to adaptively select more saliency-related features. First, we propose a cross-modality feature modulation (cmFM) module to enhance feature representations by taking the depth features as prior, which models the complementary relations of RGB-D data. Second, we propose an adaptive feature selection (AFS) module to select saliency-related features and suppress the inferior ones. The AFS module exploits multi-modality spatial feature fusion with the self-modality and cross-modality interdependencies of channel features are considered. Third, we employ a saliency-guided position-edge attention (sg-PEA) module to encourage our network to focus more on saliency-related regions. The above modules as a whole, called cmMS block, facilitates the refinement of saliency features in a coarse-to-fine fashion. Coupled with a bottom-up inference, the refined saliency features enable accurate and edge-preserving SOD. Extensive experiments demonstrate that our network outperforms stateof-the-art saliency detectors on six popular RGB-D SOD benchmarks.

show abstract

Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection

Chen

2020

Lecture Notes in Computer Science

131

View full text Add to dashboard Cite

Select, Supplement and Focus for RGB-D Saliency Detection

Cited by 194 publications

References 30 publications

RGB-D salient object detection: A survey

RGB-D salient object detection: A survey

RGB-D Salient Object Detection with Cross-Modality Modulation and Selection

Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection

Contact Info

Product

Resources

About