Li, Fei-Fei and Fergus, Rob and Perona, Pietro (2003) A Bayesian approach to unsupervised one-shot learning of object categories. In: Ninth IEEE International Conference on Computer Vision. IEEE , Los Alamitos, CA, pp. 1134-1141. ISBN 0-7695-1950-4 http://resolver.caltech.edu/CaltechAUTHORS:20111014-133823674
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20111014-133823674
Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing hundreds of parameters. We present a method for learning object categories from just a few images (1 ~ 5). It is based on incorporating "generic" knowledge which may be obtained from previously learnt models of unrelated categories. We operate in a variational Bayesian framework: object categories are represented by probabilistic models, and "prior" knowledge is represented as a probability density function on the parameters of these models. The "posterior" model for an object category is obtained by updating the prior in the light of one or more observations. Our ideas are demonstrated on four diverse categories (human faces, airplanes, motorcycles, spotted cats). Initially three categories are learnt from hundreds of training examples, and a "prior" is estimated from these. Then the model of the fourth category is learnt from 1 to 5 training examples, and is used for detecting new exemplars a set of test images.
|Item Type:||Book Section|
|Additional Information:||© 2003 IEEE. Issue Date: 13-16 Oct. 2003. Date of Current Version: 03 April 2008. We would like to thank David MacKay, Brian Ripley and Yaser Abu-Mostafa for their most useful discussions.|
|Other Numbering System:|
|Official Citation:||Li Fe-Fei; Fergus, R.; Perona, P.; , "A Bayesian approach to unsupervised one-shot learning of object categories," Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on , vol., no., pp.1134-1141 vol.2, 13-16 Oct. 2003 doi: 10.1109/ICCV.2003.1238476 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1238476&isnumber=27772|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||14 Oct 2011 20:50|
|Last Modified:||23 Aug 2016 10:06|
Repository Staff Only: item control page