Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer
Abstract
Learning object categories from small samples is a challenging problem, where machine learning tools can in general provide very few guarantees. Exploiting prior knowledge may be useful to reproduce the human capability of recognizing objects even from only one single view. This paper presents an SVM-based model adaptation algorithm able to select and weight appropriately prior knowledge coming from different categories. The method relies on the solution of a convex optimization problem which ensures to have the minimal leave-one-out error on the training set. Experiments on a subset of the Caltech-256 database show that the proposed method produces better results than both choosing one single prior model, and transferring from all previous experience in a flat uninformative way.
Cite
Text
Tommasi et al. "Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540064Markdown
[Tommasi et al. "Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/tommasi2010cvpr-safety/) doi:10.1109/CVPR.2010.5540064BibTeX
@inproceedings{tommasi2010cvpr-safety,
title = {{Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer}},
author = {Tommasi, Tatiana and Orabona, Francesco and Caputo, Barbara},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {3081-3088},
doi = {10.1109/CVPR.2010.5540064},
url = {https://mlanthology.org/cvpr/2010/tommasi2010cvpr-safety/}
}