Fast multiscale image segmentation

By Eitan Sharon, Achi Brandt, Ronen Basri. Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 2000

318 citations recorded by the source corpus.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/2da16530f5a379b0c2b98f28cecef8f646bf9525

How researchers see this paper

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

In Biophysics

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

Towards Automatic Concept-based Explanations (2019, methodology): “interested their importance measures. Our method leverages multi-resolution image segmentation methods to There has been a long line of research on multiscale and hierarchical segmentation of images ([23, 30, 4]). In this work, we use the SLIC [2] superpixel segmentation method for its simplicity, m”
TurboPixels: Fast Superpixels Using Geometric Flows (2009, background): “In [20], a further reduction in complexity by a factor of ffiffiffiffi ffi N p is achieved, based on a recursive coarsening of the segmentation problem.”
Class-Specific, Top-Down Segmentation (2002, unknown): “[14],[1]).”
Image Segmentation with Ratio Cut (2003, methodology): “This lemma shows that any minimum-ratio-cut problem with nonnegative second edge weights can be reduced to a minimum-ratio-cut problem with positive second edge weights.”
Advanced Coarsening Schemes for Graph Partitioning (2012, background): “To the best of our knowledge, the existing multilevel algorithms for combinatorial optimization problems (such as k-partitioning, linear ordering, clustering, and segmentation) can be divided into two classes: contraction-based schemes [24,9,15] (including contractions of small subsets of nodes [3])”
General highly accurate algebraic coarsening. (2000, background): “In the case of the more general coarsening (2), a compatible relaxation scheme can be formed by relaxing simultaneously two (or more) variables at a time, in a way that keeps P i ki u i unchanged for all k. Generally, each step of the compatible scheme will consist of several (O(1)) simultaneous…”
Relaxation-based coarsening and multiscale graph organization (2010, unknown): “Following the weighted aggregation scheme used in [43], the edge connecting two coarse aggregates, p = I ( i ) and q = I ( j ), is assigned with the weight w ( coarse ) pq = k (cid:54) = l P ki w kl P lj .”
Robust Object Detection with Interleaved Categorization and Segmentation (2008, background): “State-of-the-art segmentation methods combine grouping of similar image regions with splitting processes concerned with ﬁnding most likely borders (Shi and Malik 1997; Sharon et al. 2000; Malik et al. 2001).”
The Comparative Research on Image Segmentation Algorithms (2009, methodology): “Generally, two basic methods are applied to objective evaluation of image segmentation: analytical technique and experimental technique [16].”
Efficient hierarchical graph-based video segmentation (2010, background): “These descriptors offer a much richer description of appearance than local per-pixel measurements (even if gathered in a multi-scale manner as in [17]).”
Learning full pairwise affinities for spectral segmentation (2010, unknown): “This region-based segmentation has the benefit of using more informative features extracted from the pixels inside the regions, as well as transferring local information to a larger image area with connections across regions.”
Pylon Model for Semantic Segmentation (2011, background): “Segmentation trees have been investigated for a long time, and several efficient algorithms have been developed [1, 2, 38, 27].”
Spectral segmentation with multiscale graph decomposition (2005, methodology): “[9] uses an algebraic multi-grid method for solving the normalized cut criterion efﬁciently, and uses recursive graph coars-ening to produce irregular pyramid encoding region based grouping cues.”
Recovering Surface Layout from an Image (2007, background): “Other possibilities include varying the cues used for the segmentation (Rabinovich et al., 2006) or generating a hierarchical segmentation (Ahuja, 1996; Sharon et al., 2000; Arbelaez, 2006).”