Sciweavers

707 search results - page 1 / 142
» Non-Local Contrastive Objectives
Sort
View
ICML
2010
IEEE
13 years 4 months ago
Non-Local Contrastive Objectives
Pseudo-likelihood and contrastive divergence are two well-known examples of contrastive methods. These algorithms trade off the probability of the correct label with the probabili...
David Vickrey, Cliff Chiung-Yu Lin, Daphne Koller
ICDE
2012
IEEE
246views Database» more  ICDE 2012»
11 years 6 months ago
HiCS: High Contrast Subspaces for Density-Based Outlier Ranking
—Outlier mining is a major task in data analysis. Outliers are objects that highly deviate from regular objects in their local neighborhood. Density-based outlier ranking methods...
Fabian Keller, Emmanuel Müller, Klemens B&oum...
CVPR
2012
IEEE
11 years 6 months ago
Saliency filters: Contrast based filtering for salient region detection
Saliency estimation has become a valuable tool in image processing. Yet, existing approaches exhibit considerable variation in methodology, and it is often difficult to attribute...
Federico Perazzi, Philipp Krähenbühl, Ya...
JMLR
2012
11 years 6 months ago
Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics
We consider the task of estimating, from observed data, a probabilistic model that is parameterized by a finite number of parameters. In particular, we are considering the situat...
Michael Gutmann, Aapo Hyvärinen
SCIA
2009
Springer
140views Image Analysis» more  SCIA 2009»
13 years 10 months ago
Fast Prototype Based Noise Reduction
This paper introduces a novel method for noise reduction in medical images based on concepts of the Non-Local Means algorithm. The main objective has been to develop a method that ...
Kajsa Tibell, Hagen Spies, Magnus Borga