Sciweavers

90 search results - page 4 / 18
» Semi-Supervised Learning with Very Few Labeled Training Exam...
Sort
View
CVPR
2010
IEEE
14 years 2 months ago
Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer
Learning object categories from small samples is a challenging problem, where machine learning tools can in general provide very few guarantees. Exploiting prior knowledge may be ...
Tatiana Tommasi, Francesco Orabona, Barbara Caputo
VMV
2008
107views Visualization» more  VMV 2008»
13 years 8 months ago
Learning with Few Examples using a Constrained Gaussian Prior on Randomized Trees
Machine learning with few training examples always leads to over-fitting problems, whereas human individuals are often able to recognize difficult object categories from only one ...
Erik Rodner, Joachim Denzler
NIPS
2000
13 years 8 months ago
Kernel Expansions with Unlabeled Examples
Modern classification applications necessitate supplementing the few available labeled examples with unlabeled examples to improve classification performance. We present a new tra...
Martin Szummer, Tommi Jaakkola
NLE
2008
108views more  NLE 2008»
13 years 6 months ago
Using automatically labelled examples to classify rhetorical relations: an assessment
Being able to identify which rhetorical relations (e.g., contrast or explanation) hold between spans of text is important for many natural language processing applications. Using ...
Caroline Sporleder, Alex Lascarides
ICCV
2005
IEEE
14 years 8 months ago
Building a Classification Cascade for Visual Identification from One Example
Object identification (OID) is specialized recognition where the category is known (e.g. cars) and the algorithm recognizes an object's exact identity (e.g. Bob's BMW). ...
Andras Ferencz, Erik G. Learned-Miller, Jitendra M...