Depth Enhanced Saliency Detection Method

Cheng, Ying; Fu, Huazhu; Wei, Xingxing; Xiao, Jiangjian; Cao, Xiaochun

doi:10.1145/2632856.2632866

Cited by 306 publications

(229 citation statements)

References 18 publications

Supporting

Mentioning

229

Contrasting

Order By: Relevance

“…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%

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

Chen

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

318

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: Methodsmentioning

confidence: 99%

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

Chen

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

318

315

View full text Add to dashboard Cite

show abstract

“…There have been many attempts to boost the performance of RGB methods [23,29,[37][38][39]. Depth contains structural information and 3D layout information, which have been introduced to SOD [8,10,26,32,34,44,45]. Decent progress has been made by RGB-D saliency detection methods, especially in complex scenes.…”

Section: Related Workmentioning

confidence: 99%

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Zhang

Piao

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Most methods for RGB-D salient object detection (SOD) utilize the same fusion strategy to explore the cross-modal complementary information at each level. However, this may ignore di erent feature contributions from two modalities on di erent levels towards prediction. In this paper, we propose a novel top-down multi-level fusion structure where di erent fusion strategies are utilized to e ectively explore the low-level and high-level features. This is achieved by designing the interweave fusion module (IFM) to effectively integrate the global information and designing the gated select fusion module (GSFM) to discriminatively select useful local information by ltering out the unnecessary one from RGB and depth data. Moreover, we propose an adaptive fusion module (AFM) to reintegrate the fused cross-modal features of each level to predict a more accurate result. Comprehensive experiments on 7 challenging benchmark datasets demonstrate that our method achieves the competitive performance over 14 state-of-the-art RGB-D alternative methods. CCS CONCEPTS • Computing methodologies → Interest point and salient region detections.

show abstract

“…Datasets. We evaluate the performance of the proposed saliency detection algorithm on two RGBD standard datasets: RGBD1* [5] and RGBD2* [15]. RGBD1* has 135 indoor images taken by Kinect with the resolution of 640 × 480.…”

Section: Datasets and Evaluation Indicatorsmentioning

confidence: 99%

“…Recently, advances in 3D data acquisition techniques have motivated the adoption of structural features, improving the discrimination between different objects with the similar appearance. some algorithms [19,15,5,6,44,40] adopt depth cue to deal with the challenging scenarios. In [19], Zhu et al propose a framework based on cognitive neuroscience, and use depth cue to represent the depth of real field.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A multilayer backpropagation saliency detection algorithm and its applications

Zhu

2018

Multimed Tools Appl

View full text Add to dashboard Cite

Saliency detection is an active topic in the multimedia field. Most previous works on saliency detection focus on 2D images. However, these methods are not robust against complex scenes which contain multiple objects or complex backgrounds. Recently, depth information supplies a powerful cue for saliency detection. In this paper, we propose a multilayer backpropagation saliency detection algorithm based on depth mining by which we exploit depth cue from three different layers of images. The proposed algorithm shows a good performance and maintains the robustness in complex situations. Experiments results show that the proposed framework is superior to other existing saliency approaches. Besides, we give two innovative applications by this algorithm, such as scene reconstruction from multiple images and small target object detection in video.

show abstract

Depth Enhanced Saliency Detection Method

Cited by 306 publications

References 18 publications

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

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

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

A multilayer backpropagation saliency detection algorithm and its applications

Contact Info

Product

Resources

About