Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning
This work addresses the annotation challenge in 3D point cloud segmentation for computer vision applications, representing an incremental improvement over existing weakly supervised approaches.
The paper tackles the problem of large intra-class variations in 3D point cloud segmentation by proposing a multi-prototype learning method to handle subclasses within semantic classes, achieving validated efficacy in weakly supervised tasks, especially at low-label regimes.
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large unlabeled data points. A fundamental challenge here lies in the large intra-class variations of local geometric structure, resulting in subclasses within a semantic class. In this work, we leverage this intuition and opt for maintaining an individual classifier for each subclass. Technically, we design a multi-prototype classifier, each prototype serves as the classifier weights for one subclass. To enable effective updating of multi-prototype classifier weights, we propose two constraints respectively for updating the prototypes w.r.t. all point features and for encouraging the learning of diverse prototypes. Experiments on weakly supervised 3D point cloud segmentation tasks validate the efficacy of proposed method in particular at low-label regime. Our hypothesis is also verified given the consistent discovery of semantic subclasses at no cost of additional annotations.