Results 1  10
of
49
Image Segmentation with A Bounding Box Prior
"... Userprovided object bounding box is a simple and popular interaction paradigm considered by many existing interactive image segmentation frameworks. However, these frameworks tend to exploit the provided bounding box merely to exclude its exterior from consideration and sometimes to initialize the ..."
Abstract

Cited by 77 (7 self)
 Add to MetaCart
(Show Context)
Userprovided object bounding box is a simple and popular interaction paradigm considered by many existing interactive image segmentation frameworks. However, these frameworks tend to exploit the provided bounding box merely to exclude its exterior from consideration and sometimes to initialize the energy minimization. In this paper, we discuss how the bounding box can be further used to impose a powerful topological prior, which prevents the solution from excessive shrinking and ensures that the userprovided box bounds the segmentation in a sufficiently tight way. The prior is expressed using hard constraints incorporated into the global energy minimization framework leading to an NPhard integer program. We then investigate the possible optimization strategies including linear relaxation as well as a new graph cut algorithm called pinpointing. The latter can be used either as a rounding method for the fractional LP solution, which is provably better than thresholdingbased rounding, or as a fast standalone heuristic. We evaluate the proposed algorithms on a publicly available dataset, and demonstrate the practical benefits of the new prior both qualitatively and quantitatively. 1.
Decision Tree Fields
"... This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields (CRF) which have been widely used in computer vision. In a typical CRF model the unary potentials are derived from soph ..."
Abstract

Cited by 43 (8 self)
 Add to MetaCart
(Show Context)
This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields (CRF) which have been widely used in computer vision. In a typical CRF model the unary potentials are derived from sophisticated random forest or boosting based classifiers, however, the pairwise potentials are assumed to (1) have a simple parametric form with a prespecified and fixed dependence on the image data, and (2) to be defined on the basis of a small and fixed neighborhood. In contrast, in DTF, local interactions between multiple variables are determined by means of decision trees evaluated on the image data, allowing the interactions to be adapted to the image content. This results in powerful graphical models which are able to represent complex label structure. Our key technical contribution is to show that the DTF model can be trained efficiently and jointly using a convex approximate likelihood function, enabling us to learn over a million free model parameters. We show experimentally that for applications which have a rich and complex label structure, our model achieves excellent results. 1.
Geodesic Star Convexity for Interactive Image Segmentation
"... In this paper we introduce a new shape constraint for interactive image segmentation. It is an extension of Veksler’s [25] starconvexity prior, in two ways: from a single star to multiple stars and from Euclidean rays to Geodesic paths. Global minima of the energy function are obtained subject to t ..."
Abstract

Cited by 36 (2 self)
 Add to MetaCart
(Show Context)
In this paper we introduce a new shape constraint for interactive image segmentation. It is an extension of Veksler’s [25] starconvexity prior, in two ways: from a single star to multiple stars and from Euclidean rays to Geodesic paths. Global minima of the energy function are obtained subject to these new constraints. We also introduce Geodesic Forests, which exploit the structure of shortest paths in implementing the extended constraints. The starconvexity prior is used here in an interactive setting and this is demonstrated in a practical system. The system is evaluated by means of a “robot user ” to measure the amount of interaction required in a precise way. We also introduce a new and harder dataset which augments the existing Grabcut dataset [1] with images and ground truth taken from the PASCAL VOC segmentation challenge [7]. 1.
Efficiently Selecting Regions for Scene Understanding
, 2010
"... Recent advances in scene understanding and related tasks have highlighted the importance of using regions to reason about highlevel scene structure. Typically, the regions are selected beforehand and then an energy function is defined over them. This two step process suffers from the following defi ..."
Abstract

Cited by 34 (2 self)
 Add to MetaCart
Recent advances in scene understanding and related tasks have highlighted the importance of using regions to reason about highlevel scene structure. Typically, the regions are selected beforehand and then an energy function is defined over them. This two step process suffers from the following deficiencies: (i) the regions may not match the boundaries of the scene entities, thereby introducing errors; and (ii) as the regions are obtained without any knowledge of the energy function, they may not be suitable for the task at hand. We address these problems by designing an efficient approach for obtaining the best set of regions in terms of the energy function itself. Each iteration of our algorithm selects regions from a large dictionary by solving an accurate linear programming relaxation via dual decomposition. The dictionary of regions is constructed by merging and intersecting segments obtained from multiple bottomup oversegmentations. To demonstrate the usefulness of our algorithm, we consider the task of scene segmentation and show significant improvements over state of the art methods.
Submodularity beyond submodular energies: coupling edges in graph cuts
 IN CVPR
, 2011
"... We propose a new family of nonsubmodular global energy functions that still use submodularity internally to couple edges in a graph cut. We show it is possible to develop an efficient approximation algorithm that, thanks to the internal submodularity, can use standard graph cuts as a subroutine. We ..."
Abstract

Cited by 32 (17 self)
 Add to MetaCart
We propose a new family of nonsubmodular global energy functions that still use submodularity internally to couple edges in a graph cut. We show it is possible to develop an efficient approximation algorithm that, thanks to the internal submodularity, can use standard graph cuts as a subroutine. We demonstrate the advantages of edge coupling in a natural setting, namely image segmentation. In particular, for finestructured objects and objects with shading variation, our structured edge coupling leads to significant improvements over standard approaches.
Geodesic Saliency Using Background Priors
"... Abstract. Generic object level saliency detection is important for many vision tasks. Previous approaches are mostly built on the prior that “appearance contrast between objects and backgrounds is high”. Although various computational models have been developed, the problem remains challenging and h ..."
Abstract

Cited by 32 (1 self)
 Add to MetaCart
(Show Context)
Abstract. Generic object level saliency detection is important for many vision tasks. Previous approaches are mostly built on the prior that “appearance contrast between objects and backgrounds is high”. Although various computational models have been developed, the problem remains challenging and huge behavioral discrepancies between previous approaches can be observed. This suggest that the problem may still be highly illposed by using this prior only. In this work, we tackle the problem from a different viewpoint: we focus more on the background instead of the object. We exploit two common priors about backgrounds in natural images, namely boundary and connectivity priors, to provide more clues for the problem. Accordingly, we propose a novel saliency measure called geodesic saliency. It is intuitive, easy to interpret and allows fast implementation. Furthermore, it is complementary to previous approaches, because it benefits more from background priors while previous approaches do not. Evaluation on two databases validates that geodesic saliency achieves superior results and outperforms previous approaches by a large margin, in both accuracy and speed (2 ms per image). This illustrates that appropriate prior exploitation is helpful for the illposed saliency detection problem. 1
Boundary Learning by Optimization with Topological Constraints Supplementary Material
"... In this section we provide additional details of the experimental comparisons that were performed in Section 4 of the main text. We also show an extended presentation of the warping error results shown in the main text. In particular Figure 1 shows the warping error on the test set of the convolutio ..."
Abstract

Cited by 31 (5 self)
 Add to MetaCart
(Show Context)
In this section we provide additional details of the experimental comparisons that were performed in Section 4 of the main text. We also show an extended presentation of the warping error results shown in the main text. In particular Figure 1 shows the warping error on the test set of the convolutional network methods along with BEL and gPbOWTUCM. For this comparison, a threshold of gPbOWTUCM and BEL was chosen according to the threshold that achieved lowest Rand error also on the test set (shown in Figure 4 of the main text). These results are consistent with the relative ordering of algorithms that the Rand index produced, but the relative reduction in error between the methods is larger (for example, the gPbOWTUCM method has almost ten times as much warping error as the highest performer, BLOTC CN). Figure 2 also shows a visual depiction of the segmentation and boundary maps of all methods that are discussed. 1.1. Multiscale Normalized Cut Multiscale normalized cut was performed using publicly available code provided by the authors of [1]:
The shape Boltzmann machine: A strong model of object shape
 In CVPR
, 2012
"... A good model of object shape is essential in applications such as segmentation, object detection, inpainting and graphics. For example, when performing segmentation, local constraints on the shape can help where the object boundary is noisy or unclear, and global constraints can resolve ambiguities ..."
Abstract

Cited by 29 (2 self)
 Add to MetaCart
(Show Context)
A good model of object shape is essential in applications such as segmentation, object detection, inpainting and graphics. For example, when performing segmentation, local constraints on the shape can help where the object boundary is noisy or unclear, and global constraints can resolve ambiguities where background clutter looks similar to part of the object. In general, the stronger the model of shape, the more performance is improved. In this paper, we use a type of Deep Boltzmann Machine [22] that we call a Shape Boltzmann Machine (ShapeBM) for the task of modeling binary shape images. We show that the ShapeBM characterizes a strong model of shape, in that samples from the model look realistic and it can generalize to generate samples that differ from training examples. We find that the ShapeBM learns distributions that are qualitatively and quantitatively better than existing models for this task. 1.
On Parameter Learning in CrfBased Approaches to Object Class Image Segmentation
 ECCV
, 2010
"... Recent progress in perpixel object class labeling of natural images can be attributed to the use of multiple types of image features and sound statistical learning approaches. Within the latter, Conditional Random Fields (CRF) are prominently used for their ability to represent interactions betwee ..."
Abstract

Cited by 26 (4 self)
 Add to MetaCart
(Show Context)
Recent progress in perpixel object class labeling of natural images can be attributed to the use of multiple types of image features and sound statistical learning approaches. Within the latter, Conditional Random Fields (CRF) are prominently used for their ability to represent interactions between random variables. Despite their popularity in computer vision, parameter learning for CRFs has remained difficult, popular approaches being crossvalidation and piecewise training. In this work, we propose a simple yet expressive treestructured CRF based on a recent hierarchical image segmentation method. Our model combines and weights multiple image features within a hierarchical representation and allows simple and efficient globallyoptimal learning of ≈ 10 5 parameters. The tractability of our model allows us to pose and answer some of the open questions regarding parameter learning applying to CRFbased approaches. The key findings for learning CRF models are, from the obvious to the surprising, i) multiple image features always help, ii) the limiting dimension with respect to current models is the amount of training data, iii) piecewise training is competitive, iv) current methods for maxmargin training fail for models with many parameters.
Energy Minimization for Linear Envelope MRFs
"... Markov random fields with higher order potentials have emerged as a powerful model for several problems in computer vision. In order to facilitate their use, we propose a new representation for higher order potentials as upper and lower envelopes of linear functions. Our representation concisely mod ..."
Abstract

Cited by 26 (8 self)
 Add to MetaCart
(Show Context)
Markov random fields with higher order potentials have emerged as a powerful model for several problems in computer vision. In order to facilitate their use, we propose a new representation for higher order potentials as upper and lower envelopes of linear functions. Our representation concisely models several commonly used higher order potentials, thereby providing a unified framework for minimizing the corresponding Gibbs energy functions. We exploit this framework by converting lower envelope potentials to standard pairwise functions with the addition of a small number of auxiliary variables. This allows us to minimize energy functions with lower envelope potentials using conventional algorithms such as BP, TRW and αexpansion. Furthermore, we show how the minimization of energy functions with upper envelope potentials leads to a difficult minmax problem. We address this difficulty by proposing a new message passing algorithm that solves a linear programming relaxation of the problem. Although this is primarily a theoretical paper, we demonstrate the efficacy of our approach on the binary (fg/bg) segmentation problem. 1.