Fuzzy Variant of Affinity Propagation in Comparison to Median Fuzzy c-Means

Geweniger, Tina; Zühlke, Dietlind; Hammer, Barbara; Villmann, Thomas

doi:10.1007/978-3-642-02397-2_9

“…However, the fall-off rate of the exponential function is often selected empirically. In this section, we take advantage of the messages that are propagated between superpixels for directly determining the membership probabilities [48].…”

Section: Global Saliency: the Spatial Distribution Of Colorsmentioning

confidence: 99%

A Multisize Superpixel Approach for Salient Object Detection Based on Multivariate Normal Distribution Estimation

Zhu

¹

,

Klein

²

,

Frintrop

³

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This paper presents a new method for salient object detection based on a sophisticated appearance comparison of multisize superpixels. Those superpixels are modeled by multivariate normal distributions in CIE-Lab color space, which are estimated from the pixels they comprise. This fitting facilitates an efficient application of the Wasserstein distance on the Euclidean norm ( [Formula: see text]) to measure perceptual similarity between elements. Saliency is computed in two ways. On the one hand, we compute global saliency by probabilistically grouping visually similar superpixels into clusters and rate their compactness. On the other hand, we use the same distance measure to determine local center-surround contrasts between superpixels. Then, an innovative locally constrained random walk technique that considers local similarity between elements balances the saliency ratings inside probable objects and background. The results of our experiments show the robustness and efficiency of our approach against 11 recently published state-of-the-art saliency detection methods on five widely used benchmark data sets.

show abstract

“…Affinity propagation reinforces two types of messages associated with each node, the responsibility r(i, k) and the availability a(i, k). The probability for assigning node i into the cluster represented by exemplar node k is computed by equation p(i, k) = er (i,k) , wherer is the normalized responsibility as in [Geweniger et al 2009]. …”

Section: ·mentioning

confidence: 99%

Overlapping community detection in networks

Xie

¹

,

Kelley

²

,

Szymanski

³

2013

View full text Add to dashboard Cite

This paper reviews the state of the art in overlapping community detection algorithms, quality measures, and benchmarks. A thorough comparison of different algorithms (a total of fourteen) is provided. In addition to community level evaluation, we propose a framework for evaluating algorithms' ability to detect overlapping nodes, which helps to assess over-detection and underdetection. After considering community level detection performance measured by Normalized Mutual Information, the Omega index, and node level detection performance measured by Fscore, we reached the following conclusions. For low overlapping density networks, SLPA, OSLOM, Game and COPRA offer better performance than the other tested algorithms. For networks with high overlapping density and high overlapping diversity, both SLPA and Game provide relatively stable performance. However, test results also suggest that the detection in such networks is still not yet fully resolved. A common feature observed by various algorithms in real-world networks is the relatively small fraction of overlapping nodes (typically less than 30%), each of which belongs to only 2 or 3 communities.

show abstract

“…Affinity propagation reinforces two types of messages associated with each node, the responsibility r(i, k) and the availability a(i, k). The probability for assigning node i into the cluster represented by exemplar node k is computed by equation p(i, k) = e r(i,k) , where r is the normalized responsibility as in [Geweniger et al 2009].…”

Section: With Running Time O(mkhmentioning

confidence: 99%

Overlapping Community Detection in Networks: the State of the Art and Comparative Study

Xie,

Kelley,

Szymanski

2011

Preprint

View full text Add to dashboard Cite

This paper reviews the state of the art in overlapping community detection algorithms, quality measures, and benchmarks. A thorough comparison of different algorithms (a total of fourteen) is provided. In addition to community level evaluation, we propose a framework for evaluating algorithms' ability to detect overlapping nodes, which helps to assess over-detection and underdetection. After considering community level detection performance measured by Normalized Mutual Information, the Omega index, and node level detection performance measured by Fscore, we reached the following conclusions. For low overlapping density networks, SLPA, OSLOM, Game and COPRA offer better performance than the other tested algorithms. For networks with high overlapping density and high overlapping diversity, both SLPA and Game provide relatively stable performance. However, test results also suggest that the detection in such networks is still not yet fully resolved. A common feature observed by various algorithms in real-world networks is the relatively small fraction of overlapping nodes (typically less than 30%), each of which belongs to only 2 or 3 communities.

show abstract

Fuzzy Variant of Affinity Propagation in Comparison to Median Fuzzy c-Means

Cited by 10 publications

References 7 publications

A Multisize Superpixel Approach for Salient Object Detection Based on Multivariate Normal Distribution Estimation

A Multisize Superpixel Approach for Salient Object Detection Based on Multivariate Normal Distribution Estimation

Overlapping community detection in networks

Overlapping Community Detection in Networks: the State of the Art and Comparative Study

Contact Info

Product

Resources

About