Abstract

We propose a novel Coupled Projection multi-task Met-ric Learning (CP-mtML) method for large scale face re-trieval. In contrast to previous works which were limited tolow dimensional features and small datasets, the proposed method scales to large datasets with high dimensional face descriptors. It utilises pairwise (dis-)similarity constraintsas supervision and hence does not require exhaustive class annotation for every training image. While, traditionally, multi-task learning methods have been validated on samedataset but different tasks, we work on the more chal-lenging setting with heterogeneous datasets and different tasks. We show empirical validation on multiple face im-age datasets of different facial traits, e.g. identity, age andexpression. We use classic Local Binary Pattern (LBP) de-scriptors along with the recent Deep Convolutional Neural Network (CNN) features. The experiments clearly demonstrate the scalability and improved performance of the proposed method on the tasks of identity and age based face image retrieval compared to competitive existing methods, on the standard datasets and with the presence of a million distractor face images.