Multiple Instance Learning by Discriminative Training of Markov Networks
Hossein Hajimirsadeghi, Jinling Li, Greg Mori, Mohammad Zaki, Tarek Sayed
We introduce a graphical framework for multiple instance learning (MIL) based on Markov networks. This framework can be used to model the traditional MIL definition as well as more general MIL definitions. Different levels of ambiguity -- the portion of positive instances in a bag -- can be explored in weakly supervised data. To train these models, we propose a discriminative max-margin learning algorithm leveraging efficient inference for cardinality-based cliques. The efficacy of the proposed framework is evaluated on a variety of data sets. Experimental results verify that encoding or learning the degree of ambiguity can improve classification performance.
PDF Link: /papers/13/p262-hajimirsadeghi.pdf
AUTHOR = "Hossein Hajimirsadeghi
and Jinling Li and Greg Mori and Mohammad Zaki and Tarek Sayed",
TITLE = "Multiple Instance Learning by Discriminative Training of Markov Networks",
BOOKTITLE = "Proceedings of the Twenty-Ninth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-13)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2013",
PAGES = "262--271"