Rethinking the compositionality of point clouds through regularization in the hyperbolic space

Autor:	Montanaro, Antonio, Valsesia, Diego, Magli, Enrico
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Electrical Engineering and Systems Science - Image and Video Processing
Druh dokumentu:	Working Paper
Popis:	Point clouds of 3D objects exhibit an inherent compositional nature where simple parts can be assembled into progressively more complex shapes to form whole objects. Explicitly capturing such part-whole hierarchy is a long-sought objective in order to build effective models, but its tree-like nature has made the task elusive. In this paper, we propose to embed the features of a point cloud classifier into the hyperbolic space and explicitly regularize the space to account for the part-whole hierarchy. The hyperbolic space is the only space that can successfully embed the tree-like nature of the hierarchy. This leads to substantial improvements in the performance of state-of-art supervised models for point cloud classification. Comment: NeurIPS 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2209.10318 Zobrazit plný text záznamu View this record from Arxiv