Object Localization based on Structural SVM using Privileged Information

Abstract

We propose a structured prediction algorithm for object localization based on Sup-port Vector Machines (SVMs) using privileged information. Privileged informa-tion provides useful high-level knowledge for image understanding and facilitates learning a reliable model even with a small number of training examples. In our setting, we assume that such information is available only at training time since it may be difficult to obtain from visual data accurately without human supervision. Our goal is to improve performance by incorporating privileged information into ordinary learning framework and adjusting model parameters for better general-ization. We tackle object localization problem based on a novel structural SVM using privileged information, where an alternating loss-augmented inference pro-cedure is employed to handle the term in the objective function corresponding to privileged information. We apply the proposed algorithm to the Caltech-UCSD Birds 200-2011 dataset, and obtain encouraging results suggesting further inves-tigation into the benefit of privileged information in structured prediction. 1