Cosegmentation Revisited: Models and Optimization

Vicente, Sara; Kolmogorov, Vladimir; Rother, Carsten

doi:10.1007/978-3-642-15552-9_34

Cited by 112 publications

(124 citation statements)

References 19 publications

Supporting

Mentioning

123

Contrasting

Order By: Relevance

“…8 break the submodular properties of the energy. However, this model can be solved by Dual Decomposition (DD) techniques, recently proposed for enforcing similar histogram matching constraints between foreground regions in the context of cosegmentation [23]. As above, we begin by performing a single human/non-human segmentation across all frames, and for each frame individually run α-expansion using the energy of model 1.…”

Section: Training and Inferencementioning

confidence: 99%

See 1 more Smart Citation

Human Instance Segmentation from Video using Detector-based Conditional Random Fields

Vineet

Warrell

Ladický

et al. 2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

In this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instances and background. To achieve our goal, we add three new components to their framework. First, we include human partsbased detection potentials to take advantage of the structure present in human instances. Further, in order to generate a consistent segmentation from different human parts, we incorporate shape prior information, which biases the segmentation to characteristic overall human shapes. Also, we enhance the representative power of the energy function by adopting exemplar instance based matching terms, which helps our method to adapt easily to different human sizes and poses. Finally, we extensively evaluate our proposed method on the Buffy dataset with our new segmented ground truth images, and show a substantial improvement over existing CRF methods. These new annotations will be made available for future use as well.

show abstract

Section: Training and Inferencementioning

confidence: 99%

“…10. This can be efficiently optimized by a subgradient method using the techniques of [23], where each step involves solving a submodular graphcut. A solution to the primal is not guaranteed by solving the dual (but can be recognized if the duality gap is closed).…”

Section: Training and Inferencementioning

confidence: 99%

Human Instance Segmentation from Video using Detector-based Conditional Random Fields

Vineet

Warrell

Ladický

et al. 2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

show abstract

“…In other related works, the cosegmentation approach has also been performed across image sequences [7,15]. Slightly different variations to the MRF/graph cut [5] formulations and classification framework have been proposed to perform cosegmentation or object detection [23,6,8] where the only constraint is that the objects in the foreground are similar. Moving away from completely unsupervised methods, others have improved classification rates by incorporating an element of object training [24,12] or interaction [2].…”

Section: Background and Related Workmentioning

confidence: 99%

“…However, the cosegmentation problem encompasses a large range of variability and difficulty. For example, the problem can be formulated with a completely automatic segmentation of the same object among an image pair under angle or illumination changes [19,23,21]. On the other end of the spectrum, the problem can utilize training, and/or interactive methods to segment a large number of images with high intra-object variability [24,2].…”

Section: Introductionmentioning

confidence: 99%

A hierarchical image clustering cosegmentation framework

Kim

Huang

2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Given the knowledge that the same or similar objects appear in a set of images, our goal is to simultaneously segment that object from the set of images. To solve this problem, known as the cosegmentation problem, we present a method based upon hierarchical clustering. Our framework first eliminates intra-class heterogeneity in a dataset by clustering similar images together into smaller groups. Then, from each image, our method extracts multiple levels of segmentation and creates connections between regions (e.g. superpixel) across levels to establish intra-image multi-scale constraints. Next we take advantage of the information available from other images in our group. We design and present an efficient method to create inter-image relationships, e.g. connections between image regions from one image to all other images in an image cluster. Given the intra & inter-image connections, we perform a segmentation of the group of images into foreground and background regions. Finally, we compare our segmentation accuracy to several other state-of-the-art segmentation methods on standard datasets, and also demonstrate the robustness of our method on real world data.

show abstract

“…Object discovery can also be thought of as a cosegmentation problem (see, e.g., Rother et al [13] and Vicente et al [14]). In cosegmentation, the information shared between groups of images is leveraged to improve segmentation.…”

Section: Prior Workmentioning

confidence: 99%

Object disappearance for object discovery

Mason

Marthi

Parr

2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-A useful capability for a mobile robot is the ability to recognize the objects in its environment that move and change (as distinct from background objects, which are largely stationary). This ability can improve the accuracy and reliability of localization and mapping, enhance the ability of the robot to interact with its environment, and facilitate applications such as inventory management and theft detection. Rather than viewing this task as a difficult application of object recognition methods from computer vision, this work is in line with a recent trend in the community towards unsupervised object discovery and tracking that exploits the fundamentally temporal nature of the data acquired by a robot. Unlike earlier approaches, which relied heavily upon computationally intensive techniques from mapping and computer vision, our approach combines visual features and RGB-D data in a simple and effective way to segment objects from robot sensory data. We then use a Dirichlet process to cluster and recognize objects. The performance of our approach is demonstrated in several test domains.

show abstract

Cosegmentation Revisited: Models and Optimization

Cited by 112 publications

References 19 publications

Human Instance Segmentation from Video using Detector-based Conditional Random Fields

Human Instance Segmentation from Video using Detector-based Conditional Random Fields

A hierarchical image clustering cosegmentation framework

Object disappearance for object discovery

Contact Info

Product

Resources

About