arXiv subjects

Ismail Ben Ayed

Publications and source records attributed to Ismail Ben Ayed.

151 records · Page 9Linked to original sources

arXiv2017

Kernel clustering: density biases and solutions

Kernel methods are popular in clustering due to their generality and discriminating power. However, we show that many kernel clustering criteria have density biases theoretically explaining some practically significant artifacts empirically observed in the past. For example, we provide conditions and formally prove the density mode isolation bias in kernel K-means for a common class of kernels. We call it Breiman's bias due to its similarity to the histogram mode isolation previously discovered by Breiman in decision tree learning with Gini impurity. We also extend our analysis to other popular kernel clustering methods, e.g. average/normalized cut or dominant sets, where density biases can take different forms. For example, splitting isolated points by cut-based criteria is essentially the sparsest subset bias, which is the opposite of the density mode bias. Our findings suggest that a principled solution for density biases in kernel clustering should directly address data inhomogeneity. We show that density equalization can be implicitly achieved using either locally adaptive weights or locally adaptive kernels. Moreover, density equalization makes many popular kernel clustering objectives equivalent. Our synthetic and real data experiments illustrate density biases and proposed solutions. We anticipate that theoretical understanding of kernel clustering limitations and their principled solutions will be important for a broad spectrum of data analysis applications across the disciplines.

stat.ML↗

arXiv2017

Unbiased Shape Compactness for Segmentation

We propose to constrain segmentation functionals with a dimensionless, unbiased and position-independent shape compactness prior, which we solve efficiently with an alternating direction method of multipliers (ADMM). Involving a squared sum of pairwise potentials, our prior results in a challenging high-order optimization problem, which involves dense (fully connected) graphs. We split the problem into a sequence of easier sub-problems, each performed efficiently at each iteration: (i) a sparse-matrix inversion based on Woodbury identity, (ii) a closed-form solution of a cubic equation and (iii) a graph-cut update of a sub-modular pairwise sub-problem with a sparse graph. We deploy our prior in an energy minimization, in conjunction with a supervised classifier term based on CNNs and standard regularization constraints. We demonstrate the usefulness of our energy in several medical applications. In particular, we report comprehensive evaluations of our fully automated algorithm over 40 subjects, showing a competitive performance for the challenging task of abdominal aorta segmentation in MRI.

cs.CV↗

arXiv2017

A 3D fully convolutional neural network and a random walker to segment the esophagus in CT

Precise delineation of organs at risk (OAR) is a crucial task in radiotherapy treatment planning, which aims at delivering high dose to the tumour while sparing healthy tissues. In recent years algorithms showed high performance and the possibility to automate this task for many OAR. However, for some OAR precise delineation remains challenging. The esophagus with a versatile shape and poor contrast is among these structures. To tackle these issues we propose a 3D fully (convolutional neural network (CNN) driven random walk (RW) approach to automatically segment the esophagus on CT. First, a soft probability map is generated by the CNN. Then an active contour model (ACM) is fitted on the probability map to get a first estimation of the center line. The outputs of the CNN and ACM are then used in addition to CT Hounsfield values to drive the RW. Evaluation and training was done on 50 CTs with peer reviewed esophagus contours. Results were assessed regarding spatial overlap and shape similarities. The generated contours showed a mean Dice coefficient of 0.76, an average symmetric square distance of 1.36 mm and an average Hausdorff distance of 11.68 compared to the reference. These figures translate into a very good agreement with the reference contours and an increase in accuracy compared to other methods. We show that by employing a CNN accurate estimations of esophagus location can be obtained and refined by a post processing RW step. One of the main advantages compared to previous methods is that our network performs convolutions in a 3D manner, fully exploiting the 3D spatial context and performing an efficient and precise volume-wise prediction. The whole segmentation process is fully automatic and yields esophagus delineations in very good agreement with the used gold standard, showing that it can compete with previously published methods.

cs.CV↗

arXiv2017

DOPE: Distributed Optimization for Pairwise Energies

We formulate an Alternating Direction Method of Mul-tipliers (ADMM) that systematically distributes the computations of any technique for optimizing pairwise functions, including non-submodular potentials. Such discrete functions are very useful in segmentation and a breadth of other vision problems. Our method decomposes the problem into a large set of small sub-problems, each involving a sub-region of the image domain, which can be solved in parallel. We achieve consistency between the sub-problems through a novel constraint that can be used for a large class of pair-wise functions. We give an iterative numerical solution that alternates between solving the sub-problems and updating consistency variables, until convergence. We report comprehensive experiments, which demonstrate the benefit of our general distributed solution in the case of the popular serial algorithm of Boykov and Kolmogorov (BK algorithm) and, also, in the context of non-submodular functions.

cs.CV↗

arXiv2016

Kernel Cuts: MRF meets Kernel & Spectral Clustering

We propose a new segmentation model combining common regularization energies, e.g. Markov Random Field (MRF) potentials, and standard pairwise clustering criteria like Normalized Cut (NC), average association (AA), etc. These clustering and regularization models are widely used in machine learning and computer vision, but they were not combined before due to significant differences in the corresponding optimization, e.g. spectral relaxation and combinatorial max-flow techniques. On the one hand, we show that many common applications using MRF segmentation energies can benefit from a high-order NC term, e.g. enforcing balanced clustering of arbitrary high-dimensional image features combining color, texture, location, depth, motion, etc. On the other hand, standard clustering applications can benefit from an inclusion of common pairwise or higher-order MRF constraints, e.g. edge alignment, bin-consistency, label cost, etc. To address joint energies like NC+MRF, we propose efficient Kernel Cut algorithms based on bound optimization. While focusing on graph cut and move-making techniques, our new unary (linear) kernel and spectral bound formulations for common pairwise clustering criteria allow to integrate them with any regularization functionals with existing discrete or continuous solvers.

cs.CV↗

arXiv2015

Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions

Many standard optimization methods for segmentation and reconstruction compute ML model estimates for appearance or geometry of segments, e.g. Zhu-Yuille 1996, Torr 1998, Chan-Vese 2001, GrabCut 2004, Delong et al. 2012. We observe that the standard likelihood term in these formulations corresponds to a generalized probabilistic K-means energy. In learning it is well known that this energy has a strong bias to clusters of equal size, which can be expressed as a penalty for KL divergence from a uniform distribution of cardinalities. However, this volumetric bias has been mostly ignored in computer vision. We demonstrate significant artifacts in standard segmentation and reconstruction methods due to this bias. Moreover, we propose binary and multi-label optimization techniques that either (a) remove this bias or (b) replace it by a KL divergence term for any given target volume distribution. Our general ideas apply to many continuous or discrete energy formulations in segmentation, stereo, and other reconstruction problems.

cs.CV↗

arXiv2014

Submodularization for Quadratic Pseudo-Boolean Optimization

Many computer vision problems require optimization of binary non-submodular energies. We propose a general optimization framework based on local submodular approximations (LSA). Unlike standard LP relaxation methods that linearize the whole energy globally, our approach iteratively approximates the energies locally. On the other hand, unlike standard local optimization methods (e.g. gradient descent or projection techniques) we use non-linear submodular approximations and optimize them without leaving the domain of integer solutions. We discuss two specific LSA algorithms based on "trust region" and "auxiliary function" principles, LSA-TR and LSA-AUX. These methods obtain state-of-the-art results on a wide range of applications outperforming many standard techniques such as LBP, QPBO, and TRWS. While our paper is focused on pairwise energies, our ideas extend to higher-order problems. The code is available online (http://vision.csd.uwo.ca/code/).

cs.CV↗