Parsimonious reduction of Gaussian mixture models with a variational-Bayes approach

Authors:
Pierrick Bruneau;Marc Gelgon;Fabien Picarougne
Affiliations:
Nantes University, LINA (UMR CNRS 6241), Polytech'Nantes rue C.Pauc, La Chantrerie, 44306 Nantes cedex 3, France and INRIA Atlas Project-Team, France;Nantes University, LINA (UMR CNRS 6241), Polytech'Nantes rue C.Pauc, La Chantrerie, 44306 Nantes cedex 3, France and INRIA Atlas Project-Team, France;Nantes University, LINA (UMR CNRS 6241), Polytech'Nantes rue C.Pauc, La Chantrerie, 44306 Nantes cedex 3, France
Venue:
Pattern Recognition
Year:
2010

Citing 17
Cited 6

Principles and practice of information theory

Principles and practice of information theory
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian Approaches to Gaussian Mixture Modeling

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning mixture hierarchies

Proceedings of the 1998 conference on Advances in neural information processing systems II
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

International Journal of Computer Vision
An Adaptive Version of the Boost by Majority Algorithm

Machine Learning
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Bayesian Feature and Model Selection for Gaussian Mixture Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Toward Category-Level Object Recognition (Lecture Notes in Computer Science)

Toward Category-Level Object Recognition (Lecture Notes in Computer Science)
Merging distributed database summaries

Proceedings of the sixteenth ACM conference on Conference on information and knowledge management
Latent mixture vocabularies for object categorization and segmentation

Image and Vision Computing
Combinatorial Optimization: Theory and Algorithms

Combinatorial Optimization: Theory and Algorithms
Bayesian hierarchical mixtures of experts

UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Distributed EM algorithms for density estimation and clustering in sensor networks

IEEE Transactions on Signal Processing
Gossip-Based Computation of a Gaussian Mixture Model for Distributed Multimedia Indexing

IEEE Transactions on Multimedia
Nonparametric motion characterization using causal probabilistic models for video indexing and retrieval

IEEE Transactions on Image Processing

Multiclass classification with potential function rules: Margin distribution and generalization

Pattern Recognition
A Decentralized and Robust Approach to Estimating a Probabilistic Mixture Model for Structuring Distributed Data

WI-IAT '11 Proceedings of the 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Volume 01
Maximum likelihood estimation of Gaussian mixture models using stochastic search

Pattern Recognition
The infinite Student's t-factor mixture analyzer for robust clustering and classification

Pattern Recognition
Full Length Article: A low-cost variational-Bayes technique for merging mixtures of probabilistic principal component analyzers

Information Fusion
Robust estimation of a global Gaussian mixture by decentralized aggregations of local models

Web Intelligence and Agent Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

Aggregating statistical representations of classes is an important task for current trends in scaling up learning and recognition, or for addressing them in distributed infrastructures. In this perspective, we address the problem of merging probabilistic Gaussian mixture models in an efficient way, through the search for a suitable combination of components from mixtures to be merged. We propose a new Bayesian modelling of this combination problem, in association to a variational estimation technique, that handles efficiently the model complexity issue. A main feature of the present scheme is that it merely resorts to the parameters of the original mixture, ensuring low computational cost and possibly communication, should we operate on a distributed system. Experimental results are reported on real data.