Sciweavers

629 search results - page 91 / 126
» Learning and Forgetting with Local Information of New Object...
Sort
View
PRIB
2010
Springer
242views Bioinformatics» more  PRIB 2010»
13 years 6 months ago
Consensus of Ambiguity: Theory and Application of Active Learning for Biomedical Image Analysis
Abstract. Supervised classifiers require manually labeled training samples to classify unlabeled objects. Active Learning (AL) can be used to selectively label only “ambiguous...
Scott Doyle, Anant Madabhushi
VIS
2004
IEEE
214views Visualization» more  VIS 2004»
14 years 9 months ago
Surface Reconstruction of Noisy and Defective Data Sets
We present a novel surface reconstruction algorithm that can recover high-quality surfaces from noisy and defective data sets without any normal or orientation information. A set ...
Hui Xie, Kevin T. McDonnell, Hong Qin
ICPR
2000
IEEE
14 years 9 months ago
Sign of Gaussian Curvature from Eigen Plane Using Principal Components Analysis
This paper describes a new method to recover the sign of the local Gaussian curvature at each point on the visible surface of a 3-D object. Multiple (p > 3) shaded images are a...
Shinji Fukui, Yuji Iwahori, Akira Iwata, Robert J....
JUCS
2010
176views more  JUCS 2010»
13 years 6 months ago
An Approach to Generation of Decision Rules
: Classical classification and clustering based on equivalence relations are very important tools in decision-making. An equivalence relation is usually determined by properties of...
Zhang Mingyi, Danning Li, Zhang Ying
ICML
2010
IEEE
13 years 9 months ago
A Theoretical Analysis of Feature Pooling in Visual Recognition
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
Y-Lan Boureau, Jean Ponce, Yann LeCun