This article is about recognizing handheld objects from incomplete tactile observations with a classifier trained on only visual representations. Our method is based on the deep learning (DL) architecture PointNet and a curriculum learning (CL) technique for fostering the learning of descriptors robust to partial representations of objects. The learning procedure gradually decomposes the visual point clouds to synthesize sparser and sparser input data for the model. In this manner, we were able to employ one-shot learning, using the decomposed visual point clouds as augmentations, and reduce the data-collection requirement for training. The approach allows for a gradual improvement of prediction accuracy as more tactile data become available.
