Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

CVPR
2005
IEEE

favoriteEmaildiscussreport

177views Computer Vision» more CVPR 2005»

Robust Boosting for Learning from Few Examples

14 years 6 months ago

Robust Boosting for Learning from Few Examples

Download cbcl.mit.edu

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 algorithm lacks information about which parts of the data are reliable, it has to make more robust classification functions. Using this framework, we propose a simple addition to the gentle boosting algorithm which enables it to work with only a few examples. We test this new algorithm on a variety of datasets and show convincing results.

Lior Wolf, Ian Martin

Real-time Traffic

Algorithm Lacks Information | Computer Vision | CVPR 2005 | Gentle Boosting Algorithm | Robust Classification Functions |

claim paper

Related Content

» Safety in Numbers Learning Categories from Few Examples with Multi Model Knowledge Transfe...

» Learning Effective Image Metrics from Few Pairwise Examples

» Learning with Few Examples by Transferring Feature Relevance

» Learning to Transform Time Series with a Few Examples

» PSOM Network Learning with Few Examples

» Learning with Few Examples using a Constrained Gaussian Prior on Randomized Trees

» FeatureBoost A MetaLearning Algorithm that Improves Model Robustness

» Learning the semantics of multimedia queries and concepts from a small number of examples

» Comparative object similarity for improved recognition with few or no examples

Post Info
More Details (n/a)

Added	12 Oct 2009
Updated	29 Oct 2009
Type	Conference
Year	2005
Where	CVPR
Authors	Lior Wolf, Ian Martin

Comments (0)