Results 1 - 10
of
12
A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problem
"... Seven years ago, Szeliski et al. published an influential study on energy minimization methods for Markov random fields (MRF). This study provided valuable insights in choosing the best optimization technique for certain classes of problems. While these insights remain generally useful today, the ph ..."
Abstract
-
Cited by 48 (13 self)
- Add to MetaCart
Seven years ago, Szeliski et al. published an influential study on energy minimization methods for Markov random fields (MRF). This study provided valuable insights in choosing the best optimization technique for certain classes of problems. While these insights remain generally useful today, the phenominal success of random field models means that the kinds of inference problems we solve have changed significantly. Specifically, the models today often include higher order interactions, flexible connectivity structures, large label-spaces of different cardinalities, or learned energy tables. To reflect these changes, we provide a modernized and enlarged study. We present an empirical comparison of 24 state-of-art techniques on a corpus of 2,300 energy minimization instances from 20 diverse computer vision applications. To ensure reproducibility, we evaluate all methods in the OpenGM2 framework and report extensive results regarding runtime and solution quality. Key insights from our study agree with the results of Szeliski et al. for the types of models they studied. However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.
Higher-order segmentation via multicuts
- CORR ABS/1305.6387
"... Multicuts enable to conveniently represent discrete graphical models for unsupervised and supervised image segmentation, based on local energy functions that exhibit symmetries. The basic Potts model and natural extensions thereof to higher-order models provide a prominent class of representatives, ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
Multicuts enable to conveniently represent discrete graphical models for unsupervised and supervised image segmentation, based on local energy functions that exhibit symmetries. The basic Potts model and natural extensions thereof to higher-order models provide a prominent class of representatives, that cover a broad range of segmentation problems relevant to image analysis and computer vision. We show how to take into account such higher-order terms systematically in view of computational inference, and present results of a comprehensive and competitive numerical evaluation of a variety of dedicated cutting-plane algorithms. Our results reveal ways to evaluate a significant subset of models globally optimal, with-out compromising runtime. Polynomially solvable relaxations are studied as well, along with advanced rounding schemes for post-processing.
A Co-occurrence Prior for Continuous Multi-Label Optimization
"... Abstract. To obtain high-quality segmentation results the integration of semantic information is indispensable. In contrast to existing segmentation methods which use a spatial regularizer, i.e. a local interaction between image points, the co-occurrence prior [15] imposes penalties on the co-existe ..."
Abstract
-
Cited by 4 (4 self)
- Add to MetaCart
(Show Context)
Abstract. To obtain high-quality segmentation results the integration of semantic information is indispensable. In contrast to existing segmentation methods which use a spatial regularizer, i.e. a local interaction between image points, the co-occurrence prior [15] imposes penalties on the co-existence of different labels in a segmentation. We propose a continuous domain formulation of this prior, using a convex relaxation multi-labeling approach. While the discrete approach [15] is employs minimization by sequential alpha expansions, our continuous convex formulation is solved by efficient primal-dual algorithms, which are highly parallelizable on the GPU. Also, our framework allows isotropic regularizers which do not exhibit grid bias. Experimental results on the MSRC benchmark confirm that the use of co-occurrence priors leads to drastic improvements in segmentation compared to the classical Potts model formulation when applied.
Proximity priors for variational semantic segmentation and recognition
- In ICCV Workshop
, 2013
"... Abstract In this paper, we introduce the concept of proximity priors into semantic segmentation in order to discourage the presence of certain object classes (such as 'sheep' and 'wolf') 'in the vicinity' of each other. 'Vicinity' encompasses spatial distance ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(Show Context)
Abstract In this paper, we introduce the concept of proximity priors into semantic segmentation in order to discourage the presence of certain object classes (such as 'sheep' and 'wolf') 'in the vicinity' of each other. 'Vicinity' encompasses spatial distance as well as specific spatial directions simultaneously, e.g. 'plates' are found directly above 'tables', but do not fly over them. In this sense, our approach generalizes the co-occurrence prior by Ladicky et al. [3], which does not incorporate spatial information at all, and the non-metric label distance prior by Strekalovskiy et al.
Convex optimization for scene understanding
- In ICCV Workshop
, 2013
"... Abstract In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In contrast to previous approaches we do not ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(Show Context)
Abstract In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In contrast to previous approaches we do not rely on pre-processing techniques such as object detectors or superpixels. The central idea is to integrate a hierarchical label prior and a set of convex constraints into the segmentation approach, which combine the three tasks by introducing high-level scene information. Instead of learning label co-occurrences from limited benchmark training data, the hierarchical prior comes naturally with the way humans see their surroundings.
Co-Sparse Textural Similarity for Interactive Segmentation
"... Abstract. We propose an algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation. As a key ingredient of this method, we introduce a novel textural similarity measure, which builds upon the co-sparse represent ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract. We propose an algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation. As a key ingredient of this method, we introduce a novel textural similarity measure, which builds upon the co-sparse representation of image patches. We propose a statistical MAP inference approach to merge textural similarity with information about color and location. Combined with recently developed convex multilabel optimization methods this leads to an ecient algorithm for interac-tive segmentation, which is easily parallelized on graphics hardware. The provided approach outperforms state-of-the-art interactive segmentation methods on the Graz Benchmark. 1
Nature
"... In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In contrast to previous approaches we do not rely on p ..."
Abstract
- Add to MetaCart
(Show Context)
In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In contrast to previous approaches we do not rely on pre-processing techniques such as object detectors or superpixels. The central idea is to integrate a hierarchical label prior and a set of convex constraints into the segmentation approach, which combine the three tasks by introducing high-level scene information. Instead of learning label co-occurrences from limited benchmark training data, the hierarchical prior comes naturally with the way humans see their surroundings.
Communicated by Nikos Komodakis.
, 2014
"... Abstract In this article we introduce the concept of midrange geometric constraints into semantic segmentation. We call these constraints ‘midrange ’ since they are neither global constraints, which take into account all pixels without any spatial limitation, nor are they local constraints, which on ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract In this article we introduce the concept of midrange geometric constraints into semantic segmentation. We call these constraints ‘midrange ’ since they are neither global constraints, which take into account all pixels without any spatial limitation, nor are they local constraints, which only regard single pixels or pairwise relations. Instead, the proposed constraints allow to discourage the occurrence of labels in the vicinity of each other, e.g., ‘wolf ’ and ‘sheep’. ‘Vicinity ’ encompasses spatial distance as well as specific spatial directions simultaneously, e.g., ‘plates ’ are found directly above ‘tables’, but do not fly over them. It is up to the user to specifically define the spatial extent of the constraint between each two labels. Such constraints are not only interesting for scene segmentation, but also for part-based articulated or rigid objects. The reason is that object parts such as for example arms, torso and legs usually obey specific spatial rules, which are among the few things that remain valid for articulated objects over many images and which can be expressed in terms of the proposed midrange constraints, i.e. closeness and/or direction. We show, how midrange geometric constraints are formulated within a con-tinuous multi-label optimization framework, and we give a convex relaxation, which allows us to find globally optimal
Entropy Minimization for Convex Relaxation Approaches
"... Despite their enormous success in solving hard combi-natorial problems, convex relaxation approaches often suf-fer from the fact that the computed solutions are far from binary and that subsequent heuristic binarization may sub-stantially degrade the quality of computed solutions. In this paper, we ..."
Abstract
- Add to MetaCart
(Show Context)
Despite their enormous success in solving hard combi-natorial problems, convex relaxation approaches often suf-fer from the fact that the computed solutions are far from binary and that subsequent heuristic binarization may sub-stantially degrade the quality of computed solutions. In this paper, we propose a novel relaxation technique which incor-porates the entropy of the objective variable as a measure of relaxation tightness. We show both theoretically and ex-perimentally that augmenting the objective function with an entropy term gives rise to more binary solutions and con-sequently solutions with a substantially lower optimality gap. We use difference of convex function (DC) program-ming as an efficient and provably convergent solver for the arising convex-concave minimization problem. We evalu-ate this approach on three prominent non-convex computer vision challenges: multi-label inpainting, image segmenta-tion and spatio-temporal multi-view reconstruction. These experiments show that our approach consistently yields bet-ter solutions with respect to the original integral optimiza-tion problem. 1.
1Local Optimization based Segmentation of Spatially-Recurring, Multi-Region Objects with Part Configuration Constraints
"... Abstract—The level set framework has been a popular medical image segmentation technique for many years due to its several advantages, such as parametrization independence, ease of im-plementation, extendibility from a curve in 2D to higher dimen-sions, and automatic handling of topological changes. ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—The level set framework has been a popular medical image segmentation technique for many years due to its several advantages, such as parametrization independence, ease of im-plementation, extendibility from a curve in 2D to higher dimen-sions, and automatic handling of topological changes. However, existence of noise, low contrast and objects complexity in medical images cause many segmentation algorithms (including level set-based methods) to fail. Incorporating prior knowledge into image segmentation algorithms has proven useful for obtaining more accurate and plausible results. Two important constraints, containment and exclusion of regions, have gained attention in recent years mainly due to their descriptive power and intuitive definitions. In this paper, we augment the level set framework with the ability to handle these two intuitive geometric relationships, containment and exclusion, along with a distance
