A comparison of deep multilayer networks and Markov random field matching models for face recognition in the wild

Abstract

Robustness to a diverse range of image transformations and distortions has been an everlasting goal of visual pattern recognition. While there have been a huge number of efforts to advance the state-of-the art in this direction over the last decades, two prominent outstanding schemes, among others, are deep multilayer architectures and graphical models, providing some degree of robustness to undesired image perturbations. In this study, the authors aim at shedding some light on the underlying concepts, mechanisms, strengths and potentials of each methodology while discussing their relative merits from a practical point of view. In particular, they discuss the underlying motivations for the construction of deep multilayer architectures and undirected graphical models, also known as Markov random fields. The principles in the construction of each architecture, how invariance properties are achieved in each approach, the efficiency of each approach in terms of computations required during train and test as well as the degree of human labour required in each approach are discussed. Finally, an experimental comparison of the performances of the two frameworks is performed on a challenging problem of face recognition in unconstrained settings in the presence of a wide range of undesirable visual perturbations.