Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection

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

doi:10.1109/iccv.2019.00735

Cited by 366 publications

(401 citation statements)

References 35 publications

Supporting

Mentioning

397

Contrasting

Unclassified

Order By: Relevance

“…As can be clearly observed that the proposed network significantly outperforms the competing methods across all the datasets in all the metrics except E ξ . Comparing with the recent state-of-the-art model DMRA [42], our approach increases its S α and F β scores by an average of 2.8% and 2.1%, decreases the M by an average of 1.0%, which clearly indicates the good consistence with the ground truth. We Table 5.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 65%

“…Datasets. We adopt 7 widely used RGB-D benchmark datasets for evaluation, including NJUD [24], NLPR [41], DES [8], STERE [38], LFSD [28], DUT [42], and SIP [14], which contain 1985, 1000, 135, 1000, 100, 1200, 929 well annotated images, respectively. Among them, SIP is a recent collected human activities oriented dataset with high image resolution (744×992).…”

Section: Methodsmentioning

confidence: 99%

“…We compare our model with 10 state-of-the-arts, consisting of 3 traditional methods: LHM [41], ACSD [24], LBE [16]; and 7 CNNs-based methods: DF [45], CTMF [20], MMCI [3], TAN [2], PCAN [1], CPFP [62], DMRA [42]. Note that all the results of the compared approaches are reproduced by running source codes or pre-computed by the authors.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

“…Note that all the results of the compared approaches are reproduced by running source codes or pre-computed by the authors. In addition, we also trained a model (marked with * ) using the same trainset with DMRA [42] for fair comparison.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

“…Although several novel CNN-based SOD approaches [42] [62] have been proposed for RGB-D data recently, the optimal way to fuse RGB and depth information remains an open issue, which lies in two aspects: model incompatibility and redundancy, low-quality depth map. Most of the existing fusion strategies can be classified into early fusion [45] [47], late fusion [20] [14], and middle fusion [1] [3][2] [42]. Recent researches mainly focus on the middle fusion where a separate backbone network pre-trained from ImageNet [9] is usually utilized to extract depth features, which may causes incompatible problem due to the inherent modality difference between RGB and depth image [62].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection

Chen

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

303

315

View full text Add to dashboard Cite

In this paper, we aim to develop an efficient and compact deep network for RGB-D salient object detection, where the depth image provides complementary information to boost performance in complex scenarios. Starting from a coarse initial prediction by a multi-scale residual block, we propose a progressively guided alternate refinement network to refine it. Instead of using ImageNet pre-trained backbone network, we first construct a lightweight depth stream by learning from scratch, which can extract complementary features more efficiently with less redundancy. Then, different from the existing fusion based methods, RGB and depth features are fed into proposed guided residual (GR) blocks alternately to reduce their mutual degradation. By assigning progressive guidance in the stacked GR blocks within each side-output, the false detection and missing parts can be well remedied. Extensive experiments on seven benchmark datasets demonstrate that our model outperforms existing state-of-the-art approaches by a large margin, and also shows superiority in efficiency (71 FPS) and model size (64.9 MB).

show abstract

Section: Comparison With State-of-the-artsmentioning

confidence: 65%

Section: Methodsmentioning

confidence: 99%

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection

Chen

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

303

315

View full text Add to dashboard Cite

show abstract

RGB‐D salient object detection via deep fusion of semantics and details

Zhao

Chen

Wang

et al. 2020

Computer Animation & Virtual

View full text Add to dashboard Cite

In this paper, we address RGB-D salient object detection task by jointly leveraging semantics and contour details of salient objects. We propose a novel semantics-and-details complementary fusion network to adaptively integrate cross-model and multilevel features. Specifically, we employ two kinds of fusion modules in our model, which are designed for fusing high-level semantic features and integrating contour detail features of the scene components, respectively. The semantics fusion module aggregates high-level interdependent semantic relationships by a nonlinear weighted summation of small and medium receptive fields. Meanwhile, the details module integrates multi-level contour detail features to leverage expressive details of salient objects. We achieve new state-of-the-art salient object detection results on seven RGB-D datasets, that is, STERE, NJU2000, LFSD, NLPR, SSD, DES, and SIP2019 dataset. Experimental results demonstrate that our method outperforms eleven state-of-the-art salient object detection methods. K E Y W O R D S cross-model and multilevel features, feature fusion and deep fusion, RGB-D, salient object detection

show abstract

Learning based versus heuristic based: A comparative analysis of visual saliency prediction in immersive virtual reality

Aşkın

Çelikcan

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

While visual saliency has been used for various purposes in virtual reality (VR), the efforts to properly understand the saliency mechanism in VR remain insufficient. In this paper, we present an extensive comparative analysis of learning-based and heuristic-based approaches to visual saliency prediction in immersive VR experienced using head-mounted-displays with a particular focus on the contribution of the depth cue. To this end, we use three learning-based RGB-D image saliency detection methods and two heuristic-based RGB-D image saliency detection methods on a VR dataset curated from three distinct virtual environments under two-dimensional and three-dimensional viewing conditions. Additionally, we extend the analysis by including a heuristic-based RGB video saliency detection method and its depth-infused version. The results acquired using these seven methods reveal the superiority of the learning-based RGB-D image saliency prediction methods in VR and validate the importance of the depth cue in the saliency prediction of virtual environments.

show abstract

Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection

Cited by 366 publications

References 35 publications

Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection

Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection

RGB‐D salient object detection via deep fusion of semantics and details

Learning based versus heuristic based: A comparative analysis of visual saliency prediction in immersive virtual reality

Contact Info

Product

Resources

About