Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks

Fan, Deng-Ping; Zheng, Lin; Zhang, Zhao; Zhu, Menglong; Cheng, Ming–Ming

doi:10.1109/tnnls.2020.2996406

Cited by 484 publications

(307 citation statements)

References 111 publications

Supporting

Mentioning

304

Contrasting

Unclassified

Order By: Relevance

“…Models [ 78 , 79 ] that exploit the implicit shape and contour information in depth maps to refine saliency results have shown promising performance. Deep learning-based, end-to-end RGB-D models [ 80 , 81 ] are becoming more and more popular as they can effectively exploit multi-modal correlations, and multi-layer information hierarchy for robust RGB-D saliency detection [ 82 ]. Video SOD models leverage the sequential, motion, and color appearance information contained in a video sequence to detect targets that are repeated, dynamic, and salient [ 48 ].…”

Section: Overview Of Salient Object Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Salient Object Detection Techniques in Computer Vision—A Survey

Gupta

Seal

Prasad

et al. 2020

Entropy

View full text Add to dashboard Cite

Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision. The capability of automatic identification and segmentation of such salient image regions has immediate consequences for applications in the field of computer vision, computer graphics, and multimedia. A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images. These methods can be broadly categorized into two categories based on their feature engineering mechanism: conventional or deep learning-based. In this survey, most of the influential advances in image-based SOD from both conventional as well as deep learning-based categories have been reviewed in detail. Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection. Results are presented for various challenging cases for some large-scale public datasets. Different metrics considered for assessment of the performance of state-of-the-art salient object detection models are also covered. Some future directions for SOD are presented towards end.

show abstract

Section: Overview Of Salient Object Detectionmentioning

confidence: 99%

“…Recently, Reference [ 87 ] proposed a new dataset and deep learning based model for the LF-SOD task. Interested readers may refer to References [ 48 , 82 , 85 , 87 , 88 ] for further information on these related tasks.…”

Section: Overview Of Salient Object Detectionmentioning

confidence: 99%

Salient Object Detection Techniques in Computer Vision—A Survey

Gupta

Seal

Prasad

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…Tian et al [18] proposed a DMH (Depth map, Multiorder depth template, and Height difference map) representation method which can effectively capture the geometric structure information in the depth images. Fan et al [19] proposed a simple baseline architecture, called Deep Depth-Depurator Network (D3Net), which consists of a depth depurator unit and a feature learning module, performing initial low-quality depth map filtering and cross-modal feature learning respectively. The human detection algorithms effect based on deep learning are superior to other methods.…”

Section: B Rgb-d Human Detectionmentioning

confidence: 99%

“…Some scholars have jointly used RGB images and depth images for human detection [9]- [19] to solve problems such as illumination changes and complex background. Among them, Zhou et al [13] used two identical networks to process RGB images and depth images respectively, then compared the confidence scores of two network predictions and took the larger score as the final result.…”

Section: Introductionmentioning

confidence: 99%

Two-Stream RGB-D Human Detection Algorithm Based on RFB Network

et al. 2020

View full text Add to dashboard Cite

In order to effectively combine RGB image features with depth image features for human detection, this paper proposes a two-stream RGB-D human detection algorithm based on RFB network. The proposed algorithm mainly contains three parts: RGB-stream, Depth-stream and Channel Weight Fusion (CWF) strategy. (1) The RGB-stream extracts RGB image features using RFB-Net [1] as the backbone network. (2) By analyzing the results of depth features visualization, we build the Depth-stream, which can effectively extract the depth image features. (3) The improved CWF strategy can enhance the effectiveness of important channels in RGB-D fusion features and improve the capability of the network expression. The experimental results show that the proposed algorithm has a significant improvement compared with other algorithms on two common datasets.

show abstract

“…Saliency is a common research method used in computer vision. Recently, there have been many studies [10,11,40,44] based on saliency. The method of Wan et al [40] based on Zhou's [48] method.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical saliency mapping for weakly supervised object localization based on class activation mapping

Cheng

Zeng

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

Weakly supervised object localization is a basic research in the field of computer vision. In this paper, a hierarchical saliency mapping network for object localization is proposed and designed to avoid missing detailed information of potential object. Based on the classical convolution network, we remove the fully connected part and add multiple information extraction branches. The network extracts information from convolution layers of different scales to generate Hierarchical Saliency Map. Hierarchical Saliency Maps that include Hierarchical-Class Activation Map and Hierarchical-Spatial Pyramid Saliency Map fuse deep-level features and low-level features to locate object. The datasets used for testing are Caltech-UCSD Birds 200, Caltech101 and ImageNet. Compared with Class Activation Map and Spatial Pyramid Saliency Map, the localization accuracy has been improved. This method can be used for fine-grained classification, object tracking and other fields.

show abstract

Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks

Cited by 484 publications

References 111 publications

Salient Object Detection Techniques in Computer Vision—A Survey

Salient Object Detection Techniques in Computer Vision—A Survey

Two-Stream RGB-D Human Detection Algorithm Based on RFB Network

Hierarchical saliency mapping for weakly supervised object localization based on class activation mapping

Contact Info

Product

Resources

About