Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection

Zhang, Kaihua; Li, Tengpeng; Shen, Shiwen; Liu, Bo; Chen, Jin; Liu, Qingshan

doi:10.1109/cvpr42600.2020.00907

Cited by 93 publications

(38 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [40], Wang et al proposed an attentive GNN to learn the semantic and appearance relationships among several video frames for video object segmentation. Zhang et al [48] adopted a graph convolutional network to jointly implement both intra-saliency detection and inter-image correspondence for co-saliency detection. Both the latter two works constructed densely-connected pixel-pixel graphs, which are computationally expensive and lack scalability, especially for the light field data that can have more than 10 focal stack images.…”

Section: Grapth Neural Networkmentioning

confidence: 99%

“…The latter can provide external guidance for the feature update of F f . Directly constructing a densely connected graph among F f and F a , which is the case in [40,48], requires (N + 1)W H × (N + 1)W H edge connections. This scheme is computationally prohibitive for the message passing process when the feature maps have large spatial sizes.…”

Section: Dual Local Graphmentioning

confidence: 99%

“…This scheme is computationally prohibitive for the message passing process when the feature maps have large spatial sizes. The reason for [40,48] to use densely connected graphs is that the target objects in video object segmentation and co-saliency detection are usually located in different spatial locations. Thus, global context is needed.…”

Section: Dual Local Graphmentioning

confidence: 99%

See 2 more Smart Citations

Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance

Liu¹,

Zhao²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

The application of light field data in salient object detection is becoming increasingly popular recently. The difficulty lies in how to effectively fuse the features within the focal stack and how to cooperate them with the feature of the all-focus image. Previous methods usually fuse focal stack features via convolution or ConvLSTM, which are both less effective and ill-posed. In this paper, we model the information fusion within focal stack via graph networks. They introduce powerful context propagation from neighbouring nodes and also avoid ill-posed implementations. On the one hand, we construct local graph connections thus avoiding prohibitive computational costs of traditional graph networks. On the other hand, instead of processing the two kinds of data separately, we build a novel dual graph model to guide the focal stack fusion process using all-focus patterns. To handle the second difficulty, previous methods usually implement one-shot fusion for focal stack and all-focus features, hence lacking a thorough exploration of their supplements. We introduce a reciprocative guidance scheme and enable mutual guidance between these two kinds of information at multiple steps. As such, both kinds of features can be enhanced iteratively, finally benefiting the saliency prediction. Extensive experimental results show that the proposed models are all beneficial and we achieve significantly better results than state-of-the-art methods.

show abstract

Section: Grapth Neural Networkmentioning

confidence: 99%

Section: Dual Local Graphmentioning

confidence: 99%

Section: Dual Local Graphmentioning

confidence: 99%

See 1 more Smart Citation

Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance

Liu¹,

Zhao²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The omnipresence of graph data has boosted the research on graph pattern recognition and graph mining. Naturally, many GNN models have been proposed for various tasks, ranging from node classification [14,15] and link prediction [16,17] to graph clustering [18] . GNN model components include GNN architecture components (ACs), such as attention function, aggregation function, and activation function, and hyperparameters (HPs), such as drop out and learning rate.…”

Section: Introductionmentioning

confidence: 99%

Graph neural architecture search: A survey

Oloulade

Gao

Chen

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

In academia and industries, graph neural networks (GNNs) have emerged as a powerful approach to graph data processing ranging from node classification and link prediction tasks to graph clustering tasks. GNN models are usually handcrafted. However, building handcrafted GNN models is difficult and requires expert experience because GNN model components are complex and sensitive to variations. The complexity of GNN model components has brought significant challenges to the existing efficiencies of GNNs. Hence, many studies have focused on building automated machine learning frameworks to search for the best GNN models for targeted tasks. In this work, we provide a comprehensive review of automatic GNN model building frameworks to summarize the status of the field to facilitate future progress. We categorize the components of automatic GNN model building frameworks into three dimensions according to the challenges of building them. After reviewing the representative works for each dimension, we discuss promising future research directions in this rapidly growing field.

show abstract

“…SOD has been applied to many fields, including content-based image editing [1][2][3][4], image and video compression [5], object segmentation and recognition [6][7][8][9][10], visual tracking [11][12][13], image retrieval [14,15], etc. Due to their powerful ability to extract information, SOD [16,17] and other related tasks (e.g., video salient object detection [18,19], co-saliency detection [20,21], light field salient object detection [22][23][24], etc.) are often used as preprocesses in visual tasks.…”

Section: Introductionmentioning

confidence: 99%

WGI-Net: A weighted group integration network for RGB-D salient object detection

Zhang

Wang

et al. 2021

Comp. Visual Media

View full text Add to dashboard Cite

Salient object detection is used as a pre-process in many computer vision tasks (such as salient object segmentation, video salient object detection, etc.). When performing salient object detection, depth information can provide clues to the location of target objects, so effective fusion of RGB and depth feature information is important. In this paper, we propose a new feature information aggregation approach, weighted group integration (WGI), to effectively integrate RGB and depth feature information. We use a dual-branch structure to slice the input RGB image and depth map separately and then merge the results separately by concatenation. As grouped features may lose global information about the target object, we also make use of the idea of residual learning, taking the features captured by the original fusion method as supplementary information to ensure both accuracy and completeness of the fused information. Experiments on five datasets show that our model performs better than typical existing approaches for four evaluation metrics.

show abstract

Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection

Cited by 93 publications

References 46 publications

Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance

Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance

Graph neural architecture search: A survey

WGI-Net: A weighted group integration network for RGB-D salient object detection

Contact Info

Product

Resources

About