266 search results - page 13 / 54 » Learning to Identify Unexpected Instances in the Test Set |
EMNLP
2010
13 years 5 months ago
2010
We introduce a novel training algorithm for unsupervised grammar induction, called Zoomed Learning. Given a training set T and a test set S, the goal of our algorithm is to identi...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. T...
ICIAR
2005
Springer
14 years 26 days ago
2005
Springer
In this paper, a novel and efficient automatic image categorization system is proposed. This system integrates the MIL-based and global-featurebased SVMs for categorization. The IP...
CVPR
2008
IEEE
14 years 1 months ago
2008
IEEE
In this paper, we address the problem of classifying image sets, each of which contains images belonging to the same class but covering large variations in, for instance, viewpoin...
KDD
2009
ACM
14 years 8 months ago
2009
ACM
Active and semi-supervised learning are important techniques when labeled data are scarce. Recently a method was suggested for combining active learning with a semi-supervised lea...