Sciweavers

IJCV
2008

Learning to Recognize Objects with Little Supervision

13 years 11 months ago
Learning to Recognize Objects with Little Supervision
This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object class recognition when there is little supervised data, and (iii) how to formulate sensible spatial image context models using a conditional random field for integrating local features and segmentation cues (superpixels). By adopting sparse kernel methods, Bayesian learning techniques and data association with constraints, the proposed model identifies the most relevant sets of local features for recognizing object classes, achieves performance comparable to the fully supervised setting, and and obtains excellent results for image classification.
Peter Carbonetto, Gyuri Dorkó, Cordelia Sch
Added 12 Dec 2010
Updated 12 Dec 2010
Type Journal
Year 2008
Where IJCV
Authors Peter Carbonetto, Gyuri Dorkó, Cordelia Schmid, Hendrik Kück, Nando de Freitas
Comments (0)