Results 1  10
of
145
TextonBoost: Joint Appearance, Shape and Context Modeling for MultiClass Object . . .
 IN ECCV
, 2006
"... This paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently. The learned model is used for automatic visual recognition and semantic segmentation of photographs. Our discriminative model exploits nov ..."
Abstract

Cited by 426 (17 self)
 Add to MetaCart
This paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently. The learned model is used for automatic visual recognition and semantic segmentation of photographs. Our discriminative model exploits novel features, based on textons, which jointly model shape and texture. Unary classification and feature selection is achieved using shared boosting to give an efficient classifier which can be applied to a large number of classes. Accurate image segmentation is achieved by incorporating these classifiers in a conditional random field. Efficient training
Discriminative learning of Markov random fields for segmentation of 3d scan data
 In Proc. of the Conf. on Computer Vision and Pattern Recognition (CVPR
, 2005
"... We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov Random Fields (MRFs) which support efficient graphcut inference. The MRF models incorporate a large set of diverse features and enforce the preference that a ..."
Abstract

Cited by 156 (3 self)
 Add to MetaCart
(Show Context)
We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov Random Fields (MRFs) which support efficient graphcut inference. The MRF models incorporate a large set of diverse features and enforce the preference that adjacent scan points have the same classification label. We use a recently proposed maximummargin framework to discriminatively train the model from a set of labeled scans; as a result we automatically learn the relative importance of the features for the segmentation task. Performing graphcut inference in the trained MRF can then be used to segment new scenes very efficiently. We test our approach on three largescale datasets produced by different kinds of 3D sensors, showing its applicability to both outdoor and indoor environments containing diverse objects. 1.
Minimizing nonsubmodular functions with graph cuts  a review
 TPAMI
, 2007
"... Optimization techniques based on graph cuts have become a standard tool for many vision applications. These techniques allow to minimize efficiently certain energy functions corresponding to pairwise Markov Random Fields (MRFs). Currently, there is an accepted view within the computer vision communi ..."
Abstract

Cited by 145 (8 self)
 Add to MetaCart
(Show Context)
Optimization techniques based on graph cuts have become a standard tool for many vision applications. These techniques allow to minimize efficiently certain energy functions corresponding to pairwise Markov Random Fields (MRFs). Currently, there is an accepted view within the computer vision community that graph cuts can only be used for optimizing a limited class of MRF energies (e.g. submodular functions). In this survey we review some results that show that graph cuts can be applied to a much larger class of energy functions (in particular, nonsubmodular functions). While these results are wellknown in the optimization community, to our knowledge they were not used in the context of computer vision and MRF optimization. We demonstrate the relevance of these results to vision on the problem of binary texture restoration.
Accelerated training of conditional random fields with stochastic gradient methods
 In ICML
, 2006
"... We apply Stochastic MetaDescent (SMD), a stochastic gradient optimization method with gain vector adaptation, to the training of Conditional Random Fields (CRFs). On several large data sets, the resulting optimizer converges to the same quality of solution over an order of magnitude faster than lim ..."
Abstract

Cited by 141 (6 self)
 Add to MetaCart
(Show Context)
We apply Stochastic MetaDescent (SMD), a stochastic gradient optimization method with gain vector adaptation, to the training of Conditional Random Fields (CRFs). On several large data sets, the resulting optimizer converges to the same quality of solution over an order of magnitude faster than limitedmemory BFGS, the leading method reported to date. We report results for both exact and inexact inference techniques. 1.
Learning depth from single monocular images
 In NIPS 18
, 2005
"... We consider the task of depth estimation from a single monocular image. We take a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured outdoor environments which include forests, trees, buildings, etc.) and their correspond ..."
Abstract

Cited by 132 (34 self)
 Add to MetaCart
(Show Context)
We consider the task of depth estimation from a single monocular image. We take a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured outdoor environments which include forests, trees, buildings, etc.) and their corresponding groundtruth depthmaps. Then, we apply supervised learning to predict the depthmap as a function of the image. Depth estimation is a challenging problem, since local features alone are insufficient to estimate depth at a point, and one needs to consider the global context of the image. Our model uses a discriminativelytrained Markov Random Field (MRF) that incorporates multiscale local and globalimage features, and models both depths at individual points as well as the relation between depths at different points. We show that, even on unstructured scenes, our algorithm is frequently able to recover fairly accurate depthmaps. 1
A statistical model for general contextual object recog. ECCV
, 2004
"... Abstract. We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects. Given a set of images and their associated text (e.g. keywords, captions, descriptions), the objective is to ..."
Abstract

Cited by 129 (7 self)
 Add to MetaCart
(Show Context)
Abstract. We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects. Given a set of images and their associated text (e.g. keywords, captions, descriptions), the objective is to segment an image, in either a crude or sophisticated fashion, then to find the proper associations between words and regions. Previous models are limited by the scope of the representation. In particular, they fail to exploit spatial context in the images and words. We develop a more expressive model that takes this into account. We formulate a spatially consistent probabilistic mapping between continuous image feature vectors and the supplied word tokens. By learning both wordtoregion associations and object relations, the proposed model augments scene segmentations due to smoothing implicit in spatial consistency. Context introduces cycles to the undirected graph, so we cannot rely on a straightforward implementation of the EM algorithm for estimating the model parameters and densities of the unknown alignment variables. Instead, we develop an approximate EM algorithm that uses loopy belief propagation in the inference step and iterative scaling on the pseudolikelihood approximation in the parameter update step. The experiments indicate that our approximate inference and learning algorithm converges to good local solutions. Experiments on a diverse array of images show that spatial context considerably improves the accuracy of object recognition. Most significantly, spatial context combined with a nonlinear discrete object representation allows our models to cope well with oversegmented scenes. 2 Peter Carbonetto et al. 1
3D depth reconstruction from a single still image
, 2006
"... We consider the task of 3d depth estimation from a single still image. We take a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured indoor and outdoor environments which include forests, sidewalks, trees, buildings, etc ..."
Abstract

Cited by 114 (17 self)
 Add to MetaCart
(Show Context)
We consider the task of 3d depth estimation from a single still image. We take a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured indoor and outdoor environments which include forests, sidewalks, trees, buildings, etc.) and their corresponding groundtruth depthmaps. Then, we apply supervised learning to predict the value of the depthmap as a function of the image. Depth estimation is a challenging problem, since local features alone are insufficient to estimate depth at a point, and one needs to consider the global context of the image. Our model uses a hierarchical, multiscale Markov Random Field (MRF) that incorporates multiscale local and globalimage features, and models the depths and the relation between depths at different points in the image. We show that, even on unstructured scenes, our algorithm is frequently able to recover fairly accurate depthmaps. We further propose a model that incorporates both monocular cues and stereo (triangulation) cues, to obtain significantly more accurate depth estimates than is possible using either monocular or stereo cues alone.
Kernel Conditional Random Fields: Representation and Clique Selection
 IN ICML
, 2004
"... Kernel conditional random fields (KCRFs) are introduced as a framework for discriminative modeling of graphstructured data. A representer theorem for conditional graphical models is given which shows how kernel conditional random fields arise from risk minimization procedures defined using Me ..."
Abstract

Cited by 96 (5 self)
 Add to MetaCart
Kernel conditional random fields (KCRFs) are introduced as a framework for discriminative modeling of graphstructured data. A representer theorem for conditional graphical models is given which shows how kernel conditional random fields arise from risk minimization procedures defined using Mercer kernels on labeled graphs. A procedure for greedily selecting cliques in the dual representation is then proposed, which allows sparse representations. By incorporating kernels and implicit feature spaces into conditional graphical models, the framework enables semisupervised learning algorithms for structured data through the use of graph kernels.
An Introduction to Conditional Random Fields
 Foundations and Trends in Machine Learning
, 2012
"... ..."
(Show Context)
Structured prediction, dual extragradient and Bregman projections
 Journal of Machine Learning Research
, 2006
"... We present a simple and scalable algorithm for maximummargin estimation of structured output models, including an important class of Markov networks and combinatorial models. We formulate the estimation problem as a convexconcave saddlepoint problem that allows us to use simple projection methods ..."
Abstract

Cited by 59 (2 self)
 Add to MetaCart
(Show Context)
We present a simple and scalable algorithm for maximummargin estimation of structured output models, including an important class of Markov networks and combinatorial models. We formulate the estimation problem as a convexconcave saddlepoint problem that allows us to use simple projection methods based on the dual extragradient algorithm (Nesterov, 2003). The projection step can be solved using dynamic programming or combinatorial algorithms for mincost convex flow, depending on the structure of the problem. We show that this approach provides a memoryefficient alternative to formulations based on reductions to a quadratic program (QP). We analyze the convergence of the method and present experiments on two very different structured prediction tasks: 3D image segmentation and word alignment, illustrating the favorable scaling properties of our algorithm. 1 1.