2021/10/21 by Adriano Cardace, Cardace, Adriano, Riccardo Spezialetti +7
Computer Science · Earth and Planetary Sciences · #3D Surveying and Cultural Heritage #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Human Pose and Action Recognition #cs.CV
paper · pdf · doi:10.48550/arxiv.2110.11036
3DV 2021 (Oral) Code: https://github.com/CVLAB-Unibo/RefRec
arxiv created 2021/10/21 · openalex publication_date 2021/10/21 · arxiv updated 2021/10/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Unsupervised Domain Adaptation (UDA) for point cloud classification is an emerging research problem with relevant practical motivations. Reliance on multi-task learning to align features across domains has been the standard way to tackle it. In this paper, we take a different path and propose RefRec, the first approach to investigate pseudo-labels and self-training in UDA for point clouds. We present two main innovations to make self-training effective on 3D data: i) refinement of noisy pseudo-labels by matching shape descriptors that are learned by the unsupervised task of shape reconstruction on both domains; ii) a novel self-training protocol that learns domain-specific decision boundaries and reduces the negative impact of mislabelled target samples and in-domain intra-class variability. RefRec sets the new state of the art in both standard benchmarks used to test UDA for point cloud classification, showcasing the effectiveness of self-training for this important problem.