Image segmentation by figure-ground composition into maximal cliques

Ion, Adrian; Carreira, João; Sminchisescu, Cristian

doi:10.1109/iccv.2011.6126486

Cited by 38 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bottom-up segmentation methods often play an important role in the proposed algorithms [5], [6], [7], [8], [9], and thus improving segmentation techniques would entail improvements towards better computer vision applications.…”

Section: Introductionmentioning

confidence: 99%

Supervised Evaluation of Image Segmentation and Object Proposal Techniques

Pont-Tuset

Marqués

2016

IEEE Trans. Pattern Anal. Mach. Intell.

118

View full text Add to dashboard Cite

Abstract-This paper tackles the supervised evaluation of image segmentation and object proposal algorithms. It surveys, structures, and deduplicates the measures used to compare both segmentation results and object proposals with a ground truth database; and proposes a new measure: the precision-recall for objects and parts. To compare the quality of these measures, eight state-of-the-art object proposal techniques are analyzed and two quantitative meta-measures involving nine state of the art segmentation methods are presented. The meta-measures consist in assuming some plausible hypotheses about the results and assessing how well each measure reflects these hypotheses. As a conclusion of the performed experiments, this paper proposes the tandem of precision-recall curves for boundaries and for objects-and-parts as the tool of choice for the supervised evaluation of image segmentation. We make the datasets and code of all the measures publicly available.

show abstract

Section: Introductionmentioning

confidence: 99%

Supervised Evaluation of Image Segmentation and Object Proposal Techniques

Pont-Tuset

Marqués

2016

IEEE Trans. Pattern Anal. Mach. Intell.

118

View full text Add to dashboard Cite

show abstract

“…Many learning problems in vision e.g. Image Segmentation [19], Handwritten Digit Reconstruction [16], Human Pose Estimation [6] and others, can be posed as structured prediction problems. These techniques deal with complex inputs and outputs, which are governed by inherent structure and strong dependencies between different parts of a single input and output.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous Twin Kernel Learning Using Polynomial Transformations for Structured Prediction

Tonde

Elgammal

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Many learning problems in computer vision can be posed as structured prediction problems, where the input and output instances are structured objects such as trees, graphs or strings rather than, single labels {+1, −1} or scalars. Kernel methods such as Structured Support Vector Machines , Twin Gaussian Processes (TGP), Structured Gaussian Processes, and vector-valued Reproducing Kernel Hilbert Spaces (RKHS), offer powerful ways to perform learning and inference over these domains. Positive definite kernel functions allow us to quantitatively capture similarity between a pair of instances over these arbitrary domains. A poor choice of the kernel function, which decides the RKHS feature space, often results in poor performance. Automatic kernel selection methods have been developed, but have focused only on kernels on the input domain (i.e.'one-way'). In this work, we propose a novel and efficient algorithm for learning kernel functions simultaneously, on both input and output domains. We introduce the idea of learning polynomial kernel transformations, and call this method Simultaneous Twin Kernel Learning (STKL). STKL can learn arbitrary, but continuous kernel functions, including 'one-way' kernel learning as a special case. We formulate this problem for learning covariances kernels of Twin Gaussian Processes. Our experimental evaluation using learned kernels on synthetic and several real-world datasets demonstrate consistent improvement in performance of TGP's.

show abstract

“…In this paper, we tackle this by using multiple over-segmentations. Another approach works with multiple binary segmentations [20,9,14], relying on a strong assumption that each superpixel corresponds to one whole coherent region, which seems hard to achieve for real images. In [15], superpixels are incorporated in semi-supervised learning to derive a dense affinity matrix over pixels for spectral clustering, which can be computationally intensive.…”

Section: Related Workmentioning

confidence: 99%