399 search results - page 1 / 80 » Robust Boosting for Learning from Few Examples |
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
We present and analyze a novel regularization technique based on enhancing our dataset with corrupted copies of our original data. The motivation is that since the learning algori...
CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
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 ...
ICCV
2005
IEEE
13 years 11 months ago
2005
IEEE
We present a new approach to learning image metrics. The main advantage of our method lies in a formulation that requires only a few pairwise examples. Apparently, based on the li...
DAGM
2009
Springer
13 years 12 months ago
2009
Springer
The human ability to learn difficult object categories from just a few views is often explained by an extensive use of knowledge from related classes. In this work we study the use...
PAMI
2007
13 years 4 months ago
2007
We describe a semi-supervised regression algorithm that learns to transform one time series into another time series given examples of the transformation. This algorithm is applie...