Results 1 
7 of
7
Cut, Glue & Cut: A Fast, Approximate Solver for Multicut Partitioning
"... Recently, unsupervised image segmentation has become increasingly popular. Starting from a superpixel segmentation, an edgeweighted region adjacency graph is constructed. Amongst all segmentations of the graph, the one which best conforms to the given image evidence, as measured by the sum of cu ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
(Show Context)
Recently, unsupervised image segmentation has become increasingly popular. Starting from a superpixel segmentation, an edgeweighted region adjacency graph is constructed. Amongst all segmentations of the graph, the one which best conforms to the given image evidence, as measured by the sum of cut edge weights, is chosen. Since this problem is NPhard, we propose a new approximate solver based on the movemaking paradigm: first, the graph is recursively partitioned into small regions (cut phase). Then, for any two adjacent regions, we consider alternative cuts of these two regions defining possible moves (glue & cut phase). For planar problems, the optimal move can be found, whereas for nonplanar problems, efficient approximations exist. We evaluate our algorithm on published and new benchmark datasets, which we make available here. The proposed algorithm finds segmentations that, as measured by a loss function, are as close to the groundtruth as the global optimum found by exact solvers. It does so significantly faster then existing approximate methods, which is important for largescale problems. 1.
Probabilistic correlation clustering and image partitioning using perturbed multicuts
 In SSVM
, 2015
"... Abstract. We exploit recent progress on globally optimal MAP inference by integer programming and perturbationbased approximations of the logpartition function. This enables to locally represent uncertainty of image partitions by approximate marginal distributions in a mathematically substantiat ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
Abstract. We exploit recent progress on globally optimal MAP inference by integer programming and perturbationbased approximations of the logpartition function. This enables to locally represent uncertainty of image partitions by approximate marginal distributions in a mathematically substantiated way, and to rectify local data term cues so as to close contours and to obtain valid partitions. Our approach works for any graphically represented problem instance of correlation clustering, which is demonstrated by an additional social network example.
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts
"... Formulations of the Image Decomposition Problem [8] as a Multicut Problem (MP) w.r.t. a superpixel graph have received considerable attention. In contrast, instances of the MP w.r.t. a pixel grid graph have received little attention, firstly, because the MP is NPhard and instances w.r.t. a pixel gr ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
Formulations of the Image Decomposition Problem [8] as a Multicut Problem (MP) w.r.t. a superpixel graph have received considerable attention. In contrast, instances of the MP w.r.t. a pixel grid graph have received little attention, firstly, because the MP is NPhard and instances w.r.t. a pixel grid graph are hard to solve in practice, and, secondly, due to the lack of longrange terms in the objective function of the MP. We propose a generalization of the MP with longrange terms (LMP). We design and implement two efficient algorithms (primal feasible heuristics) for the MP and LMP which allow us to study instances of both problems w.r.t. the pixel grid graphs of the images in the BSDS500 benchmark [8]. The decompositions we obtain do not differ significantly from the state of the art, suggesting that the LMP is a com
Fusion moves for correlation clustering
 In CVPR
"... Correlation clustering, or multicut partitioning, is widely used in image segmentation for partitioning an undirected graph or image with positive and negative edge weights such that the sum of cut edge weights is minimized. Due to its NPhardness, exact solvers do not scale and approximative solv ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Correlation clustering, or multicut partitioning, is widely used in image segmentation for partitioning an undirected graph or image with positive and negative edge weights such that the sum of cut edge weights is minimized. Due to its NPhardness, exact solvers do not scale and approximative solvers often give unsatisfactory results. We investigate scalable methods for correlation clustering. To this end we define fusion moves for the correlation clustering problem. Our algorithm iteratively fuses the current and a proposed partitioning which monotonously improves the partitioning and maintains a valid partitioning at all times. Furthermore, it scales to larger datasets, gives near optimal solutions, and at the same time shows a good anytime performance. 1.
Motion trajectory segmentation via minimum cost multicuts
 In ICCV
, 2015
"... For the segmentation of moving objects in videos, the analysis of longterm point trajectories has been very popular recently. In this paper, we formulate the segmentation of a video sequence based on point trajectories as a minimum cost multicut problem. Unlike the commonly used spectral clusterin ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
For the segmentation of moving objects in videos, the analysis of longterm point trajectories has been very popular recently. In this paper, we formulate the segmentation of a video sequence based on point trajectories as a minimum cost multicut problem. Unlike the commonly used spectral clustering formulation, the minimum cost multicut formulation gives natural rise to optimize not only for a cluster assignment but also for the number of clusters while allowing for varying cluster sizes. In this setup, we provide a method to create a longterm point trajectory graph with attractive and repulsive binary terms and outperform stateoftheart methods based on spectral clustering on the FBMS59 dataset and on the motion subtask of the VSB100 dataset. 1.
Recent Trends in Correlation Clustering
"... Abstract The existing numeric data clustering algorithms are found limited to clustering based on the representation of data objects to be clustered. ..."
Abstract
 Add to MetaCart
Abstract The existing numeric data clustering algorithms are found limited to clustering based on the representation of data objects to be clustered.
Asymmetric Cuts: Joint Image Labeling and Partitioning
"... For image segmentation, recent advances in optimization make it possible to combine noisy region appearance terms with pairwise terms which can not only discourage, but also encourage label transitions, depending on boundary evidence. These models have the potential to overcome problems such as the ..."
Abstract
 Add to MetaCart
For image segmentation, recent advances in optimization make it possible to combine noisy region appearance terms with pairwise terms which can not only discourage, but also encourage label transitions, depending on boundary evidence. These models have the potential to overcome problems such as the shrinking bias. However, with the ability to encourage label transitions comes a different problem: strong boundary evidence can overrule weak region appearance terms to create new regions out of nowhere. While some label classes exhibit strong internal boundaries, such as the background class which is the pool of objects. Other label classes, meanwhile, should be modeled as a single region, even if some internal boundaries are visible. We therefore propose in this work to treat label classes asymmetrically: for some classes, we allow a further partitioning into their constituent objects as supported by boundary evidence; for other classes, further partitioning is forbidden. In our experiments, we show where such a model can be useful for both 2D and 3D segmentation.