Associative hierarchical CRFs for object class image segmentation

Ladický, Ľubor; Russell, Chris; Kohli, Pushmeet; Torr, Philip H. S.

doi:10.1109/iccv.2009.5459248

Cited by 450 publications

(513 citation statements)

References 23 publications

Supporting

Mentioning

509

Contrasting

Order By: Relevance

“…Ladický et al [11] showed how multiple such features and priors can be combined, avoiding the need to make an a priori decision of which is most appropriate. Their Associative Hierarchical Random Field (AHRF) model has demonstrated state of the art results for several semantic segmentation problems.…”

Section: Segmentation Priorsmentioning

confidence: 99%

A Robust Stereo Prior for Human Segmentation

Sheasby

Valentin

Crook

et al. 2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. The emergence of affordable depth cameras has enabled significant advances in human segmentation and pose estimation in recent years. While it leads to impressive results in many tasks, the use of infrared cameras have their drawbacks, in particular the fact that they don't work in direct sunlight. One alternative is to use a stereo pair of cameras to produce a disparity space image. In this work, we propose a robust method of using a disparity space image to create a prior for human segmentation. This new prior leads to greatly improved segmentation results; it can be applied to any task where a stereo pair of cameras is available, and segmentation results are desired. As an application, we show how the prior can be inserted into a dual decomposition formulation for stereo, segmentation and human pose estimation.

show abstract

Section: Segmentation Priorsmentioning

confidence: 99%

A Robust Stereo Prior for Human Segmentation

Sheasby

Valentin

Crook

et al. 2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

show abstract

“…Semantic segmentation has attracted a lot of attention, but most works have focused on the fully supervised setting, where pixel labels are given for the training images [15,14,12,21,22,26]. The basic approach was formulated in [22], where a conditional random field (CRF) was defined over image pixels with unary potentials learnt by a boosted decision tree classifier over texture-layout filters.…”

Section: Related Workmentioning

confidence: 99%

“…This problem is very challenging because the method has to recover latent pixel labels from just presence labels, before it can generalize from the training set to test images. Recently there has been significant progress in fully supervised semantic segmentation [15,14,12,21,22,26], although the problem is still unsolved. The disadvantage of fully supervised techniques is the need for manually labeling pixels in the training set, which is time consuming and expensive.…”

Section: Introductionmentioning

confidence: 99%

Weakly supervised semantic segmentation with a multi-image model

Vezhnevets

Ferrari

Buhmann

2011

2011 International Conference on Computer Vision

139

195

View full text Add to dashboard Cite

We propose a novel method for weakly supervised semantic segmentation. Training images are labeled only by the classes they contain, not by their location in the image. On test images instead, the method predicts a class label for every pixel. Our main innovation is a multi-image model (MIM) -a graphical model for recovering the pixel labels of the training images. The model connects superpixels from all training images in a data-driven fashion, based on their appearance similarity. For generalizing to new test images we integrate them into MIM using a learned multiple kernel metric, instead of learning conventional classifiers on the recovered pixel labels. We also introduce an "objectness" potential, that helps separating objects (e.g. car, dog, human) from background classes (e.g. grass, sky, road). In experiments on the MSRC 21 dataset and the LabelMe subset of [18], our technique outperforms previous weakly supervised methods and achieves accuracy comparable with fully supervised methods.

show abstract

“…Higher-order clique potentials have the capability to model complex interactions of random variables. Compared with the pairwise model, experiments [7][8][9][10][11][12][13][14] showed superior results by introducing higher-order cliques, making it essential to find an efficient algorithm to solve higher-order energies. Although many methods have been proposed, the energy forms are simple and specified, which is far behind the need of effectively describing the underlying problem.…”

Section: Introductionmentioning

confidence: 99%

“…Although many methods have been proposed, the energy forms are simple and specified, which is far behind the need of effectively describing the underlying problem. Many of existing methods simply added a specified clique term to the pairwise energy, and solved the higher-order energies using either moving making algorithms, [7][8][9]13] or belief propagation, [11] or message passing. [10,12] Such inference algorithms are scale exponentially with the size of the maximal clique in the graph.…”

Section: Introductionmentioning

confidence: 99%

Higher-order clique based image segmentation using evolutionary game theory

Li¹,

Zeng²,

Gan³

et al. 2014

AIR

View full text Add to dashboard Cite

This paper describes a novel algorithm for labeling problems of image segmentation. Beyond the pairwise model, our proposed method enables exploration on cliques, which are able to capture rich information of the scene. However, the dilemma is that, while our objective is to assign each pixel a label, the cliques are only limited to work on sets of pixels. To address this problem, the interaction between pixel and clique is studied. The labeling problem is solved using iterative scheme incorporating Expectation-Maximization (EM) algorithm that: in the E step, we would like to estimate labeling preference of pixels from clique potentials with known labeling distribution; and then update clique probabilities in the M step. We optimize the proposed function in the framework of evolutionary game theory, where the Public Goods game (PGG) is employed. Taking the advantage of large size cliques, our algorithm is able to solve multi-label segmentation problem with effective and efficiency. Quantitative evaluation and qualitative results show that our method outperforms the state-of-art. Especially, we apply the proposed algorithm on urban scene segmentation, which aims at segmenting geometric inconsistent objects via vertical assumption. We believe that our algorithm can extend to many other labeling problems.

show abstract

Associative hierarchical CRFs for object class image segmentation

Cited by 450 publications

References 23 publications

A Robust Stereo Prior for Human Segmentation

A Robust Stereo Prior for Human Segmentation

Weakly supervised semantic segmentation with a multi-image model

Higher-order clique based image segmentation using evolutionary game theory

Contact Info

Product

Resources

About