Many computer vision problems require optimization of binary non-submodular energies. In this context, iterative submodularization techniques based on trust region (LSA-TR) and auxiliary functions (LSA-AUX) have been recently proposed [9]. They achieve state-of-the-art-results on a number of computer vision applications. In this paper we extend the LSA-AUX framework in two directions. First, unlike LSA-AUX which selects auxiliary functions based solely on the current solution, we propose to incorporate several additional criteria. This results in tighter bounds for configurations that are more likely or closer to the current solution. Second, we propose move-making extensions of LSA-AUX which achieve tighter bounds by restricting the search space. Finally, we evaluate our methods on several applications. We show that for each application at least one of our extensions significantly outperforms the original LSA-AUX. Moreover, the best extension of LSA-AUX is comparable to or better than LSA-TR on five out of six applications, achieving state-of-the-arts results on four out of six applications.

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 energy 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. The proposed methods obtain state-of-the-art results on a wide range of applications such as binary deconvolution, curvature regularization, inpainting, segmentation with repulsion and two types of shape priors. Finally, we discuss a move-making extension to the LSA-TR approach. While our paper is focused on pairwise energies, our ideas extend to higher-order problems. The code is available online.

Convexity is a known important cue in human vision. We propose shape convexity as a new high-order regularization constraint for binary image segmentation. In the context of discrete optimization, object convexity is represented as a sum of three-clique potentials penalizing any 1- 0- 1 configuration on all straight lines. We show that these non-submodular potentials can be efficiently optimized using an iterative trust region approach. At each iteration the energy is linearly approximated and globally optimized within a small trust region around the current solution. While the quadratic number of all three-cliques is prohibitively high, we design a dynamic programming technique for evaluating and approximating these cliques in linear time. We also derive a second order approximation model that is more accurate but computationally intensive. We discuss limitations of our local optimization and propose gradual non-submodularization scheme that alleviates some limitations. Our experiments demonstrate general usefulness of the proposed convexity shape prior on synthetic and real image segmentation examples. Unlike standard second-order length regularization, our convexity prior does not have shrinking bias, and is robust to changes in scale and parameter selection.

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.

Curvature has received increasing attention as an important alternative to length based regularization in computer vision. In contrast to length, it preserves elongated structures and fine details. Existing approaches are either inefficient, or have low angular resolution and yield results with strong block artifacts. We derive a new model for computing squared curvature based on integral geometry. The model counts responses of straight line triple cliques. The corresponding energy decomposes into submodular and supermodular pairwise potentials. We show that this energy can be efficiently minimized even for high angular resolutions using the trust region framework. Our results confirm that we obtain accurate and visually pleasing solutions without strong artifacts at reasonable runtimes.

Several recent studies demonstrated that higher order (non-linear) functionals can yield outstanding performances in the contexts of segmentation, co-segmentation and tracking. In general, higher order functionals result in difficult problems that are not amenable to standard optimizers, and most of the existing works investigated particular forms of such functionals. In this study, we derive general bounds for a broad class of higher order functionals. By introducing auxiliary variables and invoking the Jensen's inequality as well as some convexity arguments, we prove that these bounds are auxiliary functionals for various non-linear terms, which include but are not limited to several affinity measures on the distributions or moments of segment appearance and shape, as well as soft constraints on segment volume. From these general-form bounds, we state various non-linear problems as the optimization of auxiliary functionals by graph cuts. The proposed bound optimizers are derivative-free, and consistently yield very steep functional decreases, thereby converging within a few graph cuts. We report several experiments on color and medical data, along with quantitative comparisons to state of-the-art methods. The results demonstrate competitive performances of the proposed algorithms in regard to accuracy and convergence speed, and confirm their potential in various vision and medical applications.

Trust region is a well-known general iterative approach to optimization which offers many advantages over standard gradient descent techniques. In particular, it allows more accurate nonlinear approximation models. In each iteration this approach computes a global optimum of a suitable approximation model within a fixed radius around the current solution, a.k.a. trust region. In general, this approach can be used only when some efficient constrained optimization algorithm is available for the selected non-linear (more accurate) approximation model. In this paper we propose a Fast Trust Region (FTR) approach for optimization of segmentation energies with non-linear regional terms, which are known to be challenging for existing algorithms. These energies include, but are not limited to, KL divergence and Bhattacharyya distance between the observed and the target appearance distributions, volume constraint on segment size, and shape prior constraint in a form of L2 distance from target shape moments. Our method is 1-2 orders of magnitude faster than the existing state-of-the-art methods while converging to comparable or better solutions.

Among image segmentation algorithms there are two major groups: (a) methods assuming known appearance models and (b) methods estimating appearance models jointly with segmentation. Typically, the first group optimizes appearance log-likelihoods in combination with some spacial regularization. This problem is relatively simple and many methods guarantee globally optimal results. The second group treats model parameters as additional variables transforming simple segmentation energies into high-order NP-hard functionals (Zhu-Yuille, Chan-Vese, Grab Cut, etc). It is known that such methods indirectly minimize the appearance overlap between the segments. We propose a new energy term explicitly measuring L1 distance between the object and background appearance models that can be globally maximized in one graph cut. We show that in many applications our simple term makes NP-hard segmentation functionals unnecessary. Our one cut algorithm effectively replaces approximate iterative optimization techniques based on block coordinate descent.

Radical prostatectomy is performed on approximately 40% of men with organ-confined prostate cancer. Pathologic information obtained from the prostatectomy specimen provides important prognostic information and guides recommendations for adjuvant treatment. The current pathology protocol in most centers involves primarily qualitative assessment. In this paper, we describe and evaluate our system for automatic prostate cancer detection and grading on hematoxylin & eosin-stained tissue images. Our approach is intended to address the dual challenges of large data size and the need for high-level tissue information about the locations and grades of tumors. Our system uses two stages of AdaBoost-based classification. The first provides high-level tissue component labeling of a superpixel image partitioning. The second uses the tissue component labeling to provide a classification of cancer versus noncancer, and low-grade versus high-grade cancer. We evaluated our system using 991 sub-images extracted from digital pathology images of 50 whole-mount tissue sections from 15 prostatectomy patients. We measured accuracies of 90% and 85% for the cancer versus noncancer and high-grade versus low-grade classification tasks, respectively. This system represents a first step toward automated cancer quantification on prostate digital histopathology imaging, which could pave the way for more accurately informed postprostatectomy patient care.

We propose a novel patch-based image representation that is useful because it (1) inherently detects regions with repetitive structure at multiple scales and (2) yields a parameterless hierarchical segmentation. We describe an image by breaking it into coherent regions where each region is well-described (easily reconstructed) by repeatedly instantiating a patch using a set of simple transformations. In other words, a good segment is one that has sufficient repetition of some pattern, and a patch is useful if it contains a pattern that is repeated in the image. Our criterion is naturally expressed by the well-established minimum description length (MDL) principle. MDL prefers spatially coherent regions with consistent appearance and avoids parameter tuning. We minimize the description length (in bits) of the image by encoding it with patches. Because a patch is itself an image, we measure its description length by applying the same idea recursively: encode a patch by breaking it into regions described by yet simpler patches. The resulting hierarchy of inter-dependent patches naturally leads to a hierarchical segmentation. We minimize description length over our class of image representations (all patch hierarchies / partitions). We formulate this problem as a recursive multi-label energy. Existing optimization techniques are either inapplicable or get stuck in poor local minima. We propose a new hierarchical fusion (HF) algorithm for energies containing a hierarchy of 'label costs'. Our algorithm is a contribution in itself and should be useful for this new and difficult class of energies.

Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes induced by the silhouettes in the space-time volume. We adopt a recent approach for analyzing 2D shapes and generalize it to deal with volumetric space-time action shapes. Our method utilizes properties of the solution to the Poisson equation to extract space-time features such as local space-time saliency, action dynamics, shape structure and orientation. We show that these features are useful for action recognition, detection and clustering. The method is fast, does not require video alignment and is applicable in (but not limited to) many scenarios where the background is known. Moreover, we demonstrate the robustness of our method to partial occlusions, non-rigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action, and low quality video.

We present a novel approach that allows us to reliably compute many useful properties of a silhouette. Our approach assigns, for every internal point of the silhouette, a value reflecting the mean time required for a random walk beginning at the point to hit the boundaries. This function can be computed by solving Poisson's equation, with the silhouette contours providing boundary conditions. We show how this function can be used to reliably extract various shape properties including part structure and rough skeleton, local orientation and aspect ratio of different parts, and convex and concave sections of the boundaries. In addition to this, we discuss properties of the solution and show how to efficiently compute this solution using multigrid algorithms. We demonstrate the utility of the extracted properties by using them for shape classification and retrieval.

Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes induced by the silhouettes in the space-time volume. We adopt a recent approach by Gorelick et al. (2004) for analyzing 2D shapes and generalize it to deal with volumetric space-time action shapes. Our method utilizes properties of the solution to the Poisson equation to extract space-time features such as local space-time saliency, action dynamics, shape structure and orientation. We show that these features are useful for action recognition, detection and clustering. The method is fast, does not require video alignment and is applicable in (but not limited to) many scenarios where the background is known. Moreover, we demonstrate the robustness of our method to partial occlusions, non-rigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action and low quality video