Mathematical Programming: Series A and B
The nature of statistical learning theory
The nature of statistical learning theory
Yet Another Survey on Image Segmentation: Region and Boundary Information Integration
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Learning the Kernel Matrix with Semidefinite Programming
The Journal of Machine Learning Research
Large Margin Methods for Structured and Interdependent Output Variables
The Journal of Machine Learning Research
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Comparing clusterings: an axiomatic view
ICML '05 Proceedings of the 22nd international conference on Machine learning
Recovering Surface Layout from an Image
International Journal of Computer Vision
Learning to Localize Objects with Structured Output Regression
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Solution stability in linear programming relaxations: graph partitioning and unsupervised learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Cutting-plane training of structural SVMs
Machine Learning
Contour Detection and Hierarchical Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Kernelized structural SVM learning for supervised object segmentation
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
| Hi-index | 0.00 |
This paper considers a supervised image segmentation algorithm based on joint-kernelized structured prediction. In the proposed algorithm, correlation clustering over a superpixel graph is conducted using a non-linear discriminant function, where the parameters are learned by a kernelized-structured support vector machine (SSVM). For an input superpixel image, correlation clustering is used to predict the superpixel-graph edge labels that determine whether adjacent superpixel pairs should be merged or not. In previous works, the discriminant functions for structured prediction were generally chosen to be linear with the model parameter and joint feature map. However, the linear model has two limitations: complex correlations between two input-output pairs are ignored, and the joint feature map should be explicitly designed. To cope with these limitations, a nonlinear discriminant function based on a joint kernel, which eliminates the need for explicit design of the joint feature map, is considered. The proposed joint kernel is defined as a combination of an image similarity kernel and an edge-label similarity kernel, which measure the resemblance of two input images and the similarity between two edge-label pairs, respectively. Each kernel function is designed for fast computation and efficient inference. The proposed algorithm is evaluated using two segmentation benchmark datasets: the Berkeley segmentation dataset (BSDS) and Microsoft Research Cambridge dataset (MSRC). It is observed that the joint feature map implicitly embedded in the proposed joint kernel performs comparably or even better than the explicitly designed joint feature map for a linear model.