M. Pawan Kumar

Recently several generalizations of the popular latent structural SVM framework have been proposed in the lit-erature. Broadly speaking, the generalizations can be di-vided into two categories: (i) those that predict the output variables while either marginalizing the latent variables or estimating their most likely values; and (ii) those that pre-dict the output variables by minimizing an entropy-based uncertainty measure over the latent space. In order to aid their application in computer vision, we study these gen-eralizations with the aim of identifying their strengths and weaknesses. To this end, we propose a novel prediction cri-terion that includes as special cases all previous prediction criteria that have been used in the literature. Specifically, our framework’s prediction criterion minimizes the Aczél and Daròczy entropy of the output. This in turn allows us to design a learning objective that provides a unified frame-work (UF) for latent structured prediction. We develop a single optimization algorithm and empirically show that it is as effective as the more complex approaches that have been previously employed for latent structured prediction. Using this algorithm, we provide empirical evidence that lends support to prediction via the minimization of the la-tent space uncertainty. 1