712 search results - page 35 / 143 » Pruning Training Sets for Learning of Object Categories |
ICML
2005
IEEE
14 years 9 months ago
2005
IEEE
We extend the PAC-Bayes theorem to the sample-compression setting where each classifier is represented by two independent sources of information: a compression set which consists ...
CVPR
2011
IEEE
13 years 5 months ago
2011
IEEE
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
ECCV
2008
Springer
13 years 10 months ago
2008
Springer
We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, som...
ICDM
2010
IEEE
13 years 6 months ago
2010
IEEE
In active learning, where a learning algorithm has to purchase the labels of its training examples, it is often assumed that there is only one labeler available to label examples, ...
CVPR
2005
IEEE
14 years 11 months ago
2005
IEEE
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...