Hierarchy and adaptivity in segmenting visual scenes

By Eitan Sharon, Meirav Galun, D. Sharon, Ronen Basri, Achi Brandt. Nature, 2006

302 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/8c426cdfcb67d818960e64a0c4e002322d5aa14a

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Contour Detection and Hierarchical Image Segmentation (2011, methodology): “Paired with our gPb contour detector as input, our hierarchical segmentation algorithm gPb-owt-ucm [4] produces regions whose boundaries match ground truth better than those produced by other methods [7], [29], [30], [31], [32], [33], [34], [35].”
Constrained parametric min-cuts for automatic object segmentation (2010, methodology): “[30] proposed algebraic multigrid techniques for hierarchical segmentation, while Arbeláez et al.”
Streaming Hierarchical Video Segmentation (2012, unknown): “To evaluate this progress and these methods’ comparative suitability for early video oversegmentation into supervoxels, Xu and Corso [10] study five methods, with varying characteristics (segmentation by weighted aggregation (SWA) [11, 12], graph-based (GB) [13], hierarchical graph-based (GBH) [3], ”
Efficient Multilevel Brain Tumor Segmentation With Integrated Bayesian Model Classification (2008, unknown): “used to compute the clusters, but, more recently, an efficient multiscale algorithm for doing this was proposed [29]–[31] and is described in Section IV.”
Multigrid Neural Architectures (2016, background): “We focus on a coarse-to-fine aspect of efficiency, borrowing from the use of multigrid concepts in image segmentation [31, 25].”
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts (2012, background): “ground) [28], the unbalanced normalized cut (cut divided by affinity inside foreground) [32], and the boundary fraction of low cut, four binary variables signaling if the fraction of the cut is larger than a threshold, normalized by segment”
Online Video SEEDS for Temporal Window Objectness (2013, unknown): “Adding cuts are the graph-based method [5] and its hierarchical extensions [8] [17], segmentation by weighted aggregation (SWA) [12], and normalized cuts with Nystrom optimization [7].”
Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging (2013, methodology): “Another approach (Akselrod-Ballin et al., 2009) proposed to first partition the image into homogeneous regions using the segmentation-by-weighted-aggregations (SWA) algorithm (Sharon et al., 2006).”
Relaxation-based coarsening and multiscale graph organization (2010, unknown): “Indeed, as pointed out in [9], the same coarsening procedures used by the AMG solver can directly be used for eﬃcient hierarchical organizations (such as multiscale clustering) of a graph (as in [32]) or for multiscale segmentation of an image (as in [44], [45]).”
Learning full pairwise affinities for spectral segmentation (2010, methodology): “To provide a basis of comparison, the seven existing image segmentation algorithms are reported: one K-way spectral method (MNCut [18]), three region merging methods (MShift [1], GBIS [10], SWA [43]), and three contour-based methods (Canny-OWTUCM, mPb-OWT-UCM [35], gPb-OWT-UCM [33]) which make the U”