Journal Article10.1109/TPAMI.2007.70790
Learning Flexible Features for Conditional Random Fields
TL;DR: This paper presents a model capable of learning higher-order structures using a random field of parameterized features, which can be functions of arbitrary combinations of observations, labels and auxiliary hidden variables and presents a simple induction scheme to learn these features.
read more
Abstract: Extending traditional models for discriminative labeling of structured data to include higher-order structure in the labels results in an undesirable exponential increase in model complexity. In this paper, we present a model that is capable of learning such structures using a random field of parameterized features. These features can be functions of arbitrary combinations of observations, labels and auxiliary hidden variables. We also present a simple induction scheme to learn these features, which can automatically determine the complexity needed for a given data set. We apply the model to two real-world tasks, information extraction and image labeling, and compare our results to several other methods for discriminative labeling.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Fields of Experts
Stefan Roth,Michael J. Black +1 more
TL;DR: The approach provides a practical method for learning high-order Markov random field models with potential functions that extend over large pixel neighborhoods with non-linear functions of many linear filter responses.
Learning Optical Flow
Deqing Sun,Stefan Roth,John P. Lewis,Michael J. Black +3 more
- 12 Oct 2008
TL;DR: The ground truth enables us to model how the assumption of brightness constancy is violated in naturalistic sequences, resulting in a probabilistic model of "brightness inconstancy", and generalize previous high- order constancy assumptions by modeling the constancy of responses to various linear filters in a high-order random field framework.
Learning Sparse CRFs for Feature Selection and Classification of Hyperspectral Imagery
Ping Zhong,Runsheng Wang +1 more
TL;DR: An efficient sparse training method is developed, which divides the training of SCRF into the sparse trainings of two simpler classifiers, and test the accuracy, sparsity, and efficiency of the proposed model on the real-world hyperspectral image.
42
Unsupervised SAR image segmentation using high-order conditional random fields model based on product-of-experts
TL;DR: To capture SAR data information in a more completed manner in the unsupervised SAR image segmentation, HOCRF-POE model integrates the textural features and SAR scattering statistics under un supervised Bayesian framework.
24
Abnormal region detection in gastroscopic images by combining classifiers on neighboring patches
Su Zhang,Wei Yang,Yilun Wu,Rui Yao,Shi-Dan Cheng +4 more
- 12 Jul 2009
TL;DR: A flexible detection model is proposed which combines thePatch-based technique with the boosted stumps' outputs in the products of experts form to enhance the coherence of patch classifiers.
18
References
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
- 01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
53.5K
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner,Patrick Haffner +7 more
- 01 Jan 2001
TL;DR: This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.
32.7K
•Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
John Lafferty,Andrew McCallum,Fernando Pereira +2 more
- 28 Jun 2001
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
•Book
Information Theory, Inference and Learning Algorithms
David J. C. MacKay
- 06 Oct 2003
TL;DR: A fun and exciting textbook on the mathematics underpinning the most dynamic areas of modern science and engineering.