Learning to recognize objects with little supervision

Peter Carbonetto 1 Gyuri Dorkó 2 Cordelia Schmid 2 Hendrik Kück 1 Nando de Freitas 1
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : 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 obtains excellent results for image classification.
Document type :
Journal articles
Complete list of metadatas

https://hal.inria.fr/inria-00548668
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:25:44 AM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM

Links full text

Identifiers

Collections

Citation

Peter Carbonetto, Gyuri Dorkó, Cordelia Schmid, Hendrik Kück, Nando de Freitas. Learning to recognize objects with little supervision. International Journal of Computer Vision, Springer Verlag, 2008, 77 (1-3), pp.219-238. ⟨10.1007/s11263-007-0067-7⟩. ⟨inria-00548668⟩

Share

Metrics

Record views

322