Online learning for parameter selection in large scale image search

Abstract

We explore using online learning for selecting the best parameters of Bag of Words systems when searching large scale image collections. We study two algorithms for no regret online learning: Hedge algorithm that works in the full information setting, and Exp3 that works in the bandit setting. We use these algorithms for parameter selection in two scenarios: (a) using a training set to obtain weights for the different parameters, then either choosing the parameter setting with maximum weight or combining their results with weighted majority vote; (b) working fully online by selecting a parameter combination at every time step. We demonstrate the usefulness of online learning using experiments on four different real world datasets.