722 search results - page 41 / 145 » Learning from Relevant Tasks Only |
AAAI
2011
12 years 9 months ago
2011
A common approach in machine learning is to use a large amount of labeled data to train a model. Usually this model can then only be used to classify data in the same feature spac...
AAAI
2004
13 years 10 months ago
2004
Object recognition and detection represent a relevant component in cognitive computer vision systems, such as in robot vision, intelligent video surveillance systems, or multi-mod...
SCALESPACE
2007
Springer
14 years 3 months ago
2007
Springer
Incorporating shape priors in image segmentation has become a key problem in computer vision. Most existing work is limited to a linearized shape space with small deformation modes...
CVPR
2006
IEEE
14 years 11 months ago
2006
IEEE
Classification with only one labeled example per class is a challenging problem in machine learning and pattern recognition. While there have been some attempts to address this pr...
HIS
2007
13 years 10 months ago
2007
Meta-Learning has been used to relate the performance of algorithms and the features of the problems being tackled. The knowledge in Meta-Learning is acquired from a set of meta-e...