An Adaptive Affinity Graph with Subspace Pursuit for Natural Image Segmentation

Zhang, Yang; Zhang, Huiming; Yan-wen, Guo; Lin, Kai Yan; He, Jingwu

doi:10.1109/icme.2019.00143

Cited by 9 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides clustering-based methods, graph-based methods can be regarded as image perceptual grouping and organization methods which have become one of the most popular image segmentation methods. Graph-based methods are based on the fusion of the feature and spatial information, such as normalized cut (Ncut) [22], Felzenszwalb-Huttenlocher (FH) graph-based method [23], 0 -graph [4], iterative ensemble Ncut [24], multi-scale Ncut (MNcut) [25], GL-graph [5], region adjacency graph (RAG) [26], and AASP-graph [6], etc. More recently, Kim et al [27] proposed a multi-layer sparsely connected graph to effectively combine local grouping cues, and then applied semi-supervised learning to define the relevance scores between all pairs of these graph nodes as the affinities of the graph.…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…A preliminary conference version of this paper can be referred to adaptive affinity graph with subspace pursuit (AASP-graph) [6]. Compared with AASP-graph [6], this study contains: i) an adaptive fusion affinity graph named as AFAgraph is proposed to segment natural images with online lowrank representation; ii) we propose a novel global node selection strategy containing subspace-preserving representation and affinity propagation clustering. As a new algorithmic enhancement, the strategy further perfects global node selection and improves the segmentation performance; iii) we propose a NOLRR-graph to improve segmentation accuracy and reduce computational complexity; iv) we perform extensive experiments to validate the effectiveness of global node selection strategy and the NOLRR-graph.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation

Zhang¹,

Liu²,

Zhang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Affinity graph-based segmentation methods have become a major trend in computer vision. The performance of these methods rely on the constructed affinity graph, with particular emphasis on the neighborhood topology and pairwise affinities among superpixels. Due to the advantages of assimilating different graphs, a multi-scale fusion graph has a better performance than a single graph with single-scale. However, these methods ignore the noise from images which influence the accuracy of pairwise similarities. Multi-scale combinatorial grouping and graph fusion also generate a higher computational complexity. In this paper, we propose an adaptive fusion affinity graph (AFA-graph) with noise-free low-rank representation in an online manner for natural image segmentation. An input image is first over-segmented into superpixels at different scales and then filtered by the proposed improved kernel density estimation method. Moreover, we select global nodes of these superpixels on the basis of their subspace-preserving presentation, which reveals the feature distribution of superpixels exactly. To reduce time complexity while improving performance, a sparse representation of global nodes based on noise-free online lowrank representation is used to obtain a global graph at each scale. The global graph is finally used to update a local graph which is built upon all superpixels at each scale. Experimental results on the BSD300, BSD500, MSRC, SBD, and PASCAL VOC show the effectiveness of AFA-graph in comparison with state-ofthe-art approaches. The code is available at https://github.com/ Yangzhangcst/AFA-graph.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation

Zhang¹,

Liu²,

Zhang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Because the graphs can embody both spatial and feature information [4], forming an intermediate image representation for better segmentation. Some representative methods rely on building an affinity graph according to the multi-scale superpixels [5]- [8]. Especially Y. Zhang, J.…”

Section: Introductionmentioning

confidence: 99%

Affinity Fusion Graph-Based Framework for Natural Image Segmentation

Zhang

Liu

et al. 2022

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. The proposed framework combines adjacency-graphs and kernel spectral clustering based graphs (KSC-graphs) according to a new definition named affinity nodes of multi-scale superpixels. These affinity nodes are selected based on a better affiliation of superpixels, namely subspace-preserving representation which is generated by sparse subspace clustering based on subspace pursuit. Then a KSC-graph is built via a novel kernel spectral clustering to explore the nonlinear relationships among these affinity nodes. Moreover, an adjacency-graph at each scale is constructed, which is further used to update the proposed KSCgraph at affinity nodes. The fusion graph is built across different scales, and it is partitioned to obtain final segmentation result. Experimental results on the Berkeley segmentation dataset and Microsoft Research Cambridge dataset show the superiority of our framework in comparison with the state-of-the-art methods. The code is available at https://github.com/Yangzhangcst/AF-graph.

show abstract

“…Recently, there has been a surge of interest in graphbased methods. Graph reasoning has shown to have substantial practical merits for object detection [37] [38] [39], image classification [40] [41] [42], semantic segmentation [43] [44] and change detection [45] [46] [47]. Graph neural networks are powerful tools that can perform relational inference through message passing.…”

Section: Introductionmentioning

confidence: 99%

Change Detection From Synthetic Aperture Radar Images via Graph-Based Knowledge Supplement Network

Wang

Gao

Dong

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) image change detection is a vital yet challenging task in the field of remote sensing image analysis. Most previous works adopt a self-supervised method which uses pseudo-labeled samples to guide subsequent training and testing. However, deep networks commonly require many high-quality samples for parameter optimization. The noise in pseudo-labels inevitably affects the final change detection performance. To solve the problem, we propose a Graph-based Knowledge Supplement Network (GKSNet). To be more specific, we extract discriminative information from the existing labeled dataset as additional knowledge, to suppress the adverse effects of noisy samples to some extent. Afterwards, we design a graph transfer module to distill contextual information attentively from the labeled dataset to the target dataset, which bridges feature correlation between datasets. To validate the proposed method, we conducted extensive experiments on four SAR datasets, which demonstrated the superiority of the proposed GKSNet as compared to several state-of-the-art baselines. Our codes are available at https://github.com/summitgao/SAR_CD_GKSNet .

show abstract

An Adaptive Affinity Graph with Subspace Pursuit for Natural Image Segmentation

Cited by 9 publications

References 18 publications

Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation

Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation

Affinity Fusion Graph-Based Framework for Natural Image Segmentation

Change Detection From Synthetic Aperture Radar Images via Graph-Based Knowledge Supplement Network

Contact Info

Product

Resources

About