Feature Space Transfer for Data Augmentation
computer vision and pattern recognition, pp. 9090-9098, 2018.
The problem of data augmentation in feature space is considered. A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose. This architecture exploits a parametrization of the pose manifold in terms of pose and appearance. This leads to a ...More
PPT (Upload PPT)