Support Vector Machines for Multiple-Instance Learning
Abstract
This paper presents two new formulations of multiple-instance learning as a maximum margin problem. The proposed extensions of the Support Vector Machine (SVM) learning approach lead to mixed integer quadratic programs that can be solved heuristically. Our generalization of SVMs makes a state-of-the-art classification technique, including non-linear classification via kernels, available to an area that up to now has been largely dominated by special purpose methods. We present experimental results on a pharma(cid:173) ceutical data set and on applications in automated image indexing and document categorization.
Cite
Text
Andrews et al. "Support Vector Machines for Multiple-Instance Learning." Neural Information Processing Systems, 2002.Markdown
[Andrews et al. "Support Vector Machines for Multiple-Instance Learning." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/andrews2002neurips-support/)BibTeX
@inproceedings{andrews2002neurips-support,
title = {{Support Vector Machines for Multiple-Instance Learning}},
author = {Andrews, Stuart and Tsochantaridis, Ioannis and Hofmann, Thomas},
booktitle = {Neural Information Processing Systems},
year = {2002},
pages = {577-584},
url = {https://mlanthology.org/neurips/2002/andrews2002neurips-support/}
}