Entropy-based Latent Structured Output Prediction

Diane Bouchacourt (1, 2) , Sebastian Nowozin (3) , M. Pawan Kumar (1, 2)

1 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
2 CVN - Centre de vision numérique
3 Microsoft - Microsoft Research [Cambridge]

Recently several generalizations of the popular latent structural SVM framework have been proposed in the literature. Broadly speaking, the generalizations can be divided 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 predict 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 generalizations with the aim of identifying their strengths and weaknesses. To this end, we propose a novel prediction criterion 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 Dar oczy entropy of the output. This in turn allows us to design a learning objective that provides a unified framework (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 latent space uncertainty.

Domaines: Automatique / Robotique

Diane Bouchacourt, Sebastian Nowozin, M. Pawan Kumar. Entropy-based Latent Structured Output Prediction. International Conference on Computer Vision (ICCV), Dec 2015, Santiago, Chile. ⟨10.1109/ICCV.2015.334⟩. ⟨hal-01223968⟩