Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection

By Jiaxing Zhao, Yang Cao, Deng-Ping Fan, Ming-Ming Cheng, Xuanyi Li, Le Zhang. Computer Vision and Pattern Recognition, 2019

389 citations recorded by the source corpus.

The large availability of depth sensors provides valuable complementary information for salient object detection (SOD) in RGBD images. However, due to the inherent difference between RGB and depth information, extracting features from the depth channel using ImageNet pre-trained backbone models and fusing them with RGB features directly are sub-optimal. In this paper, we utilize contrast prior, which used to be a dominant cue in none deep learning based SOD approaches, into CNNs-based architecture to enhance the depth information. The enhanced depth cues are further integrated with RGB features for SOD, using a novel fluid pyramid integration, which can make better use of multi-scale cross-modal features. Comprehensive experiments on 5 challenging benchmark datasets demonstrate the superiority of the architecture CPFP over 9 state-of-the-art alternative methods.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/677c05d8c95a269e6004dc899fc44433d345e0e7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Multinomial Distribution Learning for Effective Neural Architecture Search (2019, neutral): “For the numbers of filters F and F , a common heuristic in most human designed convolutional neural networks [11, 14, 16, 27, 10, 31] is to double F whenever the spatial feature map is halved.”
Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network (2019, background): “In virtue of recent development of object detection [41, 30, 11, 9, 5, 8, 56] and segmentation [1, 55, 33, 53, 6, 7] based on CNN [15, 20, 47, 25], scene text detection has witnessed great progress [46, 42, 57, 31, 35, 49, 24].”
Camouflaged Object Detection (2020, background): “…(b) panoptic segmentation [30] (which detects generic objects [39,44] including stuff and things), (c) salient instance/object detection [16,33,61,76] (which detects objects that grasp human attention), and (d) the proposed camouﬂaged object detection task, where the goal is to detect objects…”
Pre-Trained Image Processing Transformer (2020, methodology): “For example, the backbones of object detection models [98, 97] are often pre-trained on ImageNet classiﬁcation [18].”
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, background): “Recently, visual saliency detection from RGB-D images have attracted lots of interest due to the importance of depth information in human vision system and the popularity of depth sensing technologies [61, 64].”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “datasets, including the DES [9], DCMC [11], CDCP [75], DF [38], CTMF [18], PCA [3], MMCI [5], TANet [4], CPFP [71] and DMRA [36].”
PraNet: Parallel Reverse Attention Network for Polyp Segmentation (2020, background): “‘ † ’ represents evaluation scores from [16]. further introduce four other metrics which are widely used in the ﬁeld of object detection [7,31,8,11,37,38].”
Concealed Object Detection (2021, methodology): “The flagship products that make use of SOD technology [32] are Huawei’s smartphones, which employ SOD [32] to create what they call “AI Selfies”.”
Visual Saliency Transformer (2021, background): “Some others [81, 30, 52, 31] leveraged the depth cues to generate spatial or channel attention to enhance the RGB features.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “To address this problem, Zhao et al. [72] designed a contrast-enhanced network to improve the quality of depth maps by the contrast prior.”
EGNet: Edge Guidance Network for Salient Object Detection (2019, background): “Besides, there are many works focusing on video salient object detection [12, 54] and RGB-D salient object detection [11, 66].”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, methodology): “Generally, as summarized by previous literature [4, 77], the above approaches can be divided into three categories: (a) Early-fusion [18,31,40,55], (b) late-fusion [26,60] and (c) middle-fusion [4–6 , 80 ].”
Res2Net: A New Multi-Scale Backbone Architecture (2019, background): “Multi-scale feature representations of CNNs are of great importance to a number of vision tasks including object detection [43], face analysis [4], [41], edge detection [37], semantic segmentation [6], salient object detection [34], [65], and skeleton detection [67], boosting the model performance o”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, methodology): “Some works [49], [51], [61] use the same F-”