Open AccessProceedings Article
Sampling Methods for Unsupervised Learning
Rob Fergus,Andrew Zisserman,Pietro Perona +2 more
- 01 Dec 2004
- Vol. 17, pp 433-440
TL;DR: An algorithm to overcome the local maxima problem in estimating the parameters of mixture models and compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.
read more
Abstract: We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust fitting algorithm, RANSAC, to give a data-driven stochastic learning scheme. Minimal subsets of data points, sufficient to constrain the parameters of the model, are drawn from proposal densities to discover new regions of high likelihood. The proposal densities are learnt using EM and bias the sampling toward promising solutions. The algorithm is computationally efficient, as well as effective at escaping from local maxima. We compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.
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
Clustering Weekly Patterns of Human Mobility Through Mobile Phone Data
TL;DR: This paper uses more than 800 million CDR to identify weekly patterns of human mobility through mobile phone data and proposes new indicators to characterize the dynamics of a territory.
79
•Dissertation
동적인 데이터 분포에 강인한 파라미터 추정기와 표식점 기반 위치 추정에의 응용 = Robust parameter estimators for dynamic data distribution and its application to landmark-based localization
최성록,Sung-lok Choi +1 more
- 01 Jan 2008
TL;DR: In this paper, the authors proposed parameter estimators, which estimate parameters regardless of such wrong data, and they can achieve high accuracy even in varying data distribution through adapting their iteration number based on accurate estimation of error probability distribution and relative efficiency in statistics.
2
An automated perceptual learning algorithm for determining structure-based visual prototypes of objects from internet-scale data
Lichao Chen
- 01 Jan 2015
TL;DR: This dissertation investigated the open problem of constructing part-based object representation models from very large scale image databases in an unsupervised manner and defined a network model from a full Bayesian setting that is able to find visual templates of the same part with dramatically different visual appearances.
References
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
MLESAC: A New Robust Estimator with Application to Estimating Image Geometry
TL;DR: A new robust estimator MLESAC is presented which is a generalization of the RANSAC estimator which adopts the same sampling strategy as RANSac to generate putative solutions, but chooses the solution that maximizes the likelihood rather than just the number of inliers.
2.6K
A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms
Greg C. G. Wei,Martin A. Tanner +1 more
TL;DR: Two modifications to the MCEM algorithm (the poor man's data augmentation algorithms), which allow for the calculation of the entire posterior, are presented and serve as diagnostics for the validity of the posterior distribution.
1.6K
On Bayesian Analysis of Mixtures with an Unknown Number of Components
Sylvia Richardson,Peter H.R. Green +1 more
- 01 Jan 1997
TL;DR: In this article, a hierarchical prior model is used to deal with weak prior information while avoiding the mathematical pitfalls of using improper priors in the mixture context, and a sample from the full joint distribution of all unknown variables is generated, and this can be used as a basis for a thorough presentation of many aspects of the posterior distribution.
1.3K