Abstract

In this paper, we would like to evaluate online learningalgorithms for large-scale visual recognition using state-ofthe-art features which are preselected and held fixed. Today, combinations of high-dimensional features and linear classifiers are widely used for large-scale visual recognition. Numerous so-called mid-level features have been developed and mutually compared on an experimental basis. Although various learning methods for linear classification have also been proposed in the machine learning and natural language processing literature, they have rarely beenevaluated for visual recognition. Therefore, we give guidelines via investigations of stateof-the-art online learning methods of linear classifiers. Many methods have been evaluated using toy data and natural language processing problems such as document classification. Consequently, we gave those methods a unified interpretation from the viewpoint of visual recognition. Results of controlled comparisons indicate three guidelinesthat might change the pipeline for visual recognition.