Transductive Zero-Shot Learning for 3D Point Cloud Classification
It addresses the challenge of recognizing new classes in 3D point cloud data, which is important for applications using 3D sensors, but is incremental as it adapts existing ZSL methods to a new domain.
This paper tackles the problem of zero-shot learning for 3D point cloud classification, which had not been meaningfully explored before, by extending transductive ZSL and GZSL approaches to this domain and developing a novel triplet loss that leverages unlabeled test data, achieving state-of-the-art results in 3D and demonstrating applicability to 2D image classification.
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification. To this end, a novel triplet loss is developed that takes advantage of unlabeled test data. While designed for the task of 3D point cloud classification, the method is also shown to be applicable to the more common use-case of 2D image classification. An extensive set of experiments is carried out, establishing state-of-the-art for ZSL and GZSL in the 3D point cloud domain, as well as demonstrating the applicability of the approach to the image domain.