Learning Selective Self-Mutual Attention for RGB-D Saliency Detection

Liu, Nian; Zhang, Ni; Han, Junwei

doi:10.1109/cvpr42600.2020.01377

Cited by 279 publications

(193 citation statements)

References 7 publications

Supporting

Mentioning

192

Contrasting

Unclassified

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%

“…Note that there are 1000, 300, 100, 135, 929, and 80 test samples for NLPR, LFSD, DES, SIP, GIT, and SSD, respectively. For the NJUD [56] dataset, there are 485 test images for CPFP [53], S 2 MA [41], ICNet [42], JL-DCF [43], and UC-Net [44], and 498 testing images for all other models.…”

Section: Overall 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%

“…DF [52] was the first model to introduce deep learning technology into the RGB-D based salient object detection task. More recently, various deep learning-based models [41][42][43][44][53][54][55] have focused on exploiting effective multi-modal correlations and multi-scale or level information to boost salient object detection performance. To more clearly describe the progress in the RGB-D based salient object detection field, we provide a brief chronology in Fig.…”

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