Results 1  10
of
10
Markov Random Field Modeling, Inference & Learning in Computer Vision & Image Understanding: A Survey
, 2013
"... ..."
Efficient Image and Video Colocalization with FrankWolfe Algorithm
 In ECCV
"... Abstract. In this paper, we tackle the problem of performing efficient colocalization in images and videos. Colocalization is the problem of simultaneously localizing (with bounding boxes) objects of the same class across a set of distinct images or videos. Building upon recent stateoftheart m ..."
Abstract

Cited by 13 (0 self)
 Add to MetaCart
(Show Context)
Abstract. In this paper, we tackle the problem of performing efficient colocalization in images and videos. Colocalization is the problem of simultaneously localizing (with bounding boxes) objects of the same class across a set of distinct images or videos. Building upon recent stateoftheart methods, we show how we are able to naturally incorporate temporal terms and constraints for video colocalization into a quadratic programming framework. Furthermore, by leveraging the FrankWolfe algorithm (or conditional gradient), we show how our optimization formulations for both images and videos can be reduced to solving a succession of simple integer programs, leading to increased efficiency in both memory and speed. To validate our method, we present experimental results on the PASCAL VOC 2007 dataset for images and the YouTubeObjects dataset for videos, as well as a joint combination of the two. 1
A Cooccurrence Prior for Continuous MultiLabel Optimization
"... Abstract. To obtain highquality 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 cooccurrence prior [15] imposes penalties on the coexiste ..."
Abstract

Cited by 4 (4 self)
 Add to MetaCart
(Show Context)
Abstract. To obtain highquality 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 cooccurrence prior [15] imposes penalties on the coexistence of different labels in a segmentation. We propose a continuous domain formulation of this prior, using a convex relaxation multilabeling approach. While the discrete approach [15] is employs minimization by sequential alpha expansions, our continuous convex formulation is solved by efficient primaldual 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 cooccurrence priors leads to drastic improvements in segmentation compared to the classical Potts model formulation when applied.
A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid GenerativeDescriptive Model
"... Abstract. A graph theoretic approach is proposed for object shape representation in a hierarchical compositional architecture called Compositional Hierarchy of Parts (CHOP). In the proposed approach, vocabulary learning is performed using a hybrid generativedescriptive model. First, statistical re ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract. A graph theoretic approach is proposed for object shape representation in a hierarchical compositional architecture called Compositional Hierarchy of Parts (CHOP). In the proposed approach, vocabulary learning is performed using a hybrid generativedescriptive model. First, statistical relationships between parts are learned using a Minimum Conditional Entropy Clustering algorithm. Then, selection of descriptive parts is defined as a frequent subgraph discovery problem, and solved using a Minimum Description Length (MDL) principle. Finally, part compositions are constructed using learned statistical relationships between parts and their description lengths. Shape representation and computational complexity properties of the proposed approach and algorithms are examined using six benchmark twodimensional shape image datasets. Experiments show that CHOP can employ part shareability and indexing mechanisms for fast inference of part compositions using learned shape vocabularies. Additionally, CHOP provides better shape retrieval performance than the stateoftheart shape retrieval methods.
Conditional Random Fields for Pattern Recognition Applied to Structured Data
 ALGORITHMS
, 2015
"... ..."
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 preprocessing 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 highlevel scene information. Instead of learning label cooccurrences 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
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 partbased 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 continuous multilabel optimization framework, and we give a convex relaxation, which allows us to find globally optimal
Parsimonious Labeling
"... We propose a new family of discrete energy minimization problems, which we call parsimonious labeling. Our energy function consists of unary potentials and highorder clique potentials. While the unary potentials are arbitrary, the clique potentials are proportional to the diversity of the set of u ..."
Abstract
 Add to MetaCart
(Show Context)
We propose a new family of discrete energy minimization problems, which we call parsimonious labeling. Our energy function consists of unary potentials and highorder clique potentials. While the unary potentials are arbitrary, the clique potentials are proportional to the diversity of the set of unique labels assigned to the clique. Intuitively, our energy function encourages the labeling to be parsimonious, that is, use as few labels as possible. This in turn allows us to capture useful cues for important computer vision applications such as stereo correspondence and image denoising. Furthermore, we propose an efficient graphcuts based algorithm for the parsimonious labeling problem that provides strong theoretical guarantees on the quality of the solution. Our algorithm consists of three steps. First, we approximate a given diversity using a mixture of a novel hierarchical Pn Potts model. Second, we use a divideandconquer approach for each mixture component, where each subproblem is solved using an efficient αexpansion algorithm. This provides us with a small number of putative labelings, one for each mixture component. Third, we choose the best putative labeling in terms of the energy value. Using both synthetic and standard real datasets, we show that our algorithm significantly outperforms other graphcuts based approaches. 1.
Efficient Parallel Optimization for Potts Energy with Hierarchical Fusion
"... Potts energy frequently occurs in computer vision applications. We present an efficient parallel method for optimizing Potts energy based on the extension of hierarchical fusion algorithm. Unlike previous parallel graphcut based optimization algorithms, our approach has optimality bounds even af ..."
Abstract
 Add to MetaCart
(Show Context)
Potts energy frequently occurs in computer vision applications. We present an efficient parallel method for optimizing Potts energy based on the extension of hierarchical fusion algorithm. Unlike previous parallel graphcut based optimization algorithms, our approach has optimality bounds even after a single iteration over all labels, i.e. after solving only k1 maxflow problems, where k is the number of labels. This is perhaps the minimum number of maxflow problems one has to solve to obtain a solution with optimality guarantees. Our approximation factor is O(log2 k). Although this is not as good as the factor of 2 approximation of the well known expansion algorithm, we achieve very good results in practice. In particular, we found that the results of our algorithm after one iteration are always better than the results after one iteration of the expansion algorithm. We demonstrate experimentally the computational advantages of our parallel implementation on the problem of stereo correspondence, achieving a factor of 1.5 to 2.6 speedup compared to the serial implementation. These results were obtained with a small number of processors. The expected speedups with a larger number of processors are greater. 1.
Label Configuration Priors for Continuous MultiLabel Optimization Label Configuration Priors for Continuous MultiLabel Optimization
"... We propose a general class of label configuration priors for continuous multilabel optimization problems. In contrast to MRFbased approaches, the proposed framework unifies label configuration energies such as minimum description length priors, cooccurrence priors and hierarchical label cost p ..."
Abstract
 Add to MetaCart
(Show Context)
We propose a general class of label configuration priors for continuous multilabel optimization problems. In contrast to MRFbased approaches, the proposed framework unifies label configuration energies such as minimum description length priors, cooccurrence priors and hierarchical label cost priors. Moreover, it does not require any preprocessing in terms of superpixel estimation. All problems are solved using efficient primaldual algorithms which scale better with the number of labels than the alphaexpansion method commonly used in the MRF setting. Experimental results confirm that label configuration priors lead to drastic improvements in segmentation. In particular, the hierarchical prior allows to jointly compute a semantic segmentation and a scene classification. 1.