Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Large Margin Methods for Structured and Interdependent Output Variables
The Journal of Machine Learning Research
Design and Performance of a Fault-Tolerant Real-Time CORBA Event Service
ECRTS '06 Proceedings of the 18th Euromicro Conference on Real-Time Systems
Boundary Extraction in Natural Images Using Ultrametric Contour Maps
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Figure-ground segmentation using a hierarchical conditional random field
CRV '07 Proceedings of the Fourth Canadian Conference on Computer and Robot Vision
Training structural SVMs when exact inference is intractable
Proceedings of the 25th international conference on Machine learning
Multi-Class Segmentation with Relative Location Prior
International Journal of Computer Vision
Approximate Parameter Learning in Conditional Random Fields: An Empirical Investigation
Proceedings of the 30th DAGM symposium on Pattern Recognition
Learning to Localize Objects with Structured Output Regression
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Learning CRFs Using Graph Cuts
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
International Journal of Computer Vision
Multi-class image segmentation using conditional random fields and global classification
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning
libDAI: A Free and Open Source C++ Library for Discrete Approximate Inference in Graphical Models
The Journal of Machine Learning Research
Multiscale conditional random fields for image labeling
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Exploiting inference for approximate parameter learning in discriminative fields: an empirical study
EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Factor graphs and the sum-product algorithm
IEEE Transactions on Information Theory
DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Structured Learning and Prediction in Computer Vision
Foundations and Trends® in Computer Graphics and Vision
Conditional random fields and supervised learning in automated skin lesion diagnosis
Journal of Biomedical Imaging - Special issue on Machine Learning in Medical Imaging
Structured image segmentation using kernelized features
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Learning graph laplacian for image segmentation
Transactions on Computational Science XIX
Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition
International Journal of Computer Vision
Efficient semantic image segmentation with multi-class ranking prior
Computer Vision and Image Understanding
| Hi-index | 0.00 |
Recent progress in per-pixel object class labeling of natural images can be attributed to the use of multiple types of image features and sound statistical learning approaches. Within the latter, Conditional Random Fields (CRF) are prominently used for their ability to represent interactions between random variables. Despite their popularity in computer vision, parameter learning for CRFs has remained difficult, popular approaches being cross-validation and piecewise training. In this work, we propose a simple yet expressive tree-structured CRF based on a recent hierarchical image segmentation method. Our model combines and weights multiple image features within a hierarchical representation and allows simple and efficient globally-optimal learning of ≅ 105 parameters. The tractability of our model allows us to pose and answer some of the open questions regarding parameter learning applying to CRF-based approaches. The key findings for learning CRF models are, from the obvious to the surprising, i) multiple image features always help, ii) the limiting dimension with respect to current models is the amount of training data, iii) piecewise training is competitive, iv) current methods for max-margin training fail for models with many parameters.