Li, Fei-Fei and Fergus, Rob and Perona, Pietro (2005) Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories. In: CVPR 2004: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE , Los Alamitos, CA, pp. 178-186. ISBN 0769521584 http://resolver.caltech.edu/CaltechAUTHORS:20110824-090506675
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:20110824-090506675
Current computational approaches to learning visual object categories require thousands of training images, are slow, cannot learn in an incremental manner and cannot incorporate prior information into the learning process. In addition, no algorithm presented in the literature has been tested on more than a handful of object categories. We present an method for learning object categories from just a few training images. It is quick and it uses prior information in a principled way. We test it on a dataset composed of images of objects belonging to 101 widely varied categories. Our proposed method is based on making use of prior information, assembled from (unrelated) object categories which were previously learnt. A generative probabilistic model is used, which represents the shape and appearance of a constellation of features belonging to the object. The parameters of the model are learnt incrementally in a Bayesian manner. Our incremental algorithm is compared experimentally to an earlier batch Bayesian algorithm, as well as to one based on maximum-likelihood. The incremental and batch versions have comparable classification performance on small training sets, but incremental learning is significantly faster, making real-time learning feasible. Both Bayesian methods outperform maximum likelihood on small training sets.
|Item Type:||Book Section|
|Additional Information:||© 2004 IEEE. Issue Date: 27-02 June 2004. Date of Current Version: 24 January 2005. The authors would like to thank Marc’Aurelio Ranzato and Marco Andreetto for their help in image collection.|
|Official Citation:||Li Fei-Fei; Fergus, R.; Perona, P.;, "Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories," Computer Vision and Pattern Recognition Workshop, 2004. CVPRW '04. Conference on , vol., no., pp. 178, 27-02 June 2004 doi: 10.1109/CVPR.2004.109 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1384978&isnumber=30163|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||25 Aug 2011 18:22|
|Last Modified:||27 Aug 2013 22:16|
Repository Staff Only: item control page