Privileged information-based conditional regression forest for facial feature detection

In this paper we propose a method that utilises privileged information, that is information that is available only at the training phase, in order to train Regression Forests for facial feature detection. Our method chooses the split functions at some randomly chose internal tree nodes according to the information gain calculated from the privileged information, such as head pose or gender. In this way the training patches arrive at leaves that tend to have low variance both in displacements to facial points and in privileged information. At each leaf node, we learn both the probability of the privileged information and regression models conditioned on it. During testing, the marginal probability of privileged information is estimated and the facial feature locations are localised using the appropriate conditional regression models. The proposed model is validated by comparing with very recent methods on two challenging datasets, namely Labelled Faces in the Wild and Labelled Face Parts in the Wild.

I. INTRODUCTION

A random forest is an ensemble of randomized decision trees, a classic method of inductive inference. It is easy to implement and performs very well both in terms of prediction accuracy and in terms of computational efficiency. In the last few years it has become increasingly popular and is successfully applied to various high level computer vision tasks such as action recognition [1] and image classification [2]. Particularly, there are some promising real-time applications e.g. human pose estimation [3] and facial feature detection [4].