PointMoment:Mixed-Moment-based Self-Supervised Representation Learning for 3D Point Clouds
This addresses the issue of reduced information and diversity in learned representations for point cloud data, which is incremental as it builds on existing self-supervised approaches.
The paper tackles the problem of model collapse in self-supervised representation learning for 3D point clouds by proposing PointMoment, a framework that uses a high-order mixed moment loss function instead of conventional contrastive loss, and it outperforms previous unsupervised methods on classification and segmentation tasks.
Large and rich data is a prerequisite for effective training of deep neural networks. However, the irregularity of point cloud data makes manual annotation time-consuming and laborious. Self-supervised representation learning, which leverages the intrinsic structure of large-scale unlabelled data to learn meaningful feature representations, has attracted increasing attention in the field of point cloud research. However, self-supervised representation learning often suffers from model collapse, resulting in reduced information and diversity of the learned representation, and consequently degrading the performance of downstream tasks. To address this problem, we propose PointMoment, a novel framework for point cloud self-supervised representation learning that utilizes a high-order mixed moment loss function rather than the conventional contrastive loss function. Moreover, our framework does not require any special techniques such as asymmetric network architectures, gradient stopping, etc. Specifically, we calculate the high-order mixed moment of the feature variables and force them to decompose into products of their individual moment, thereby making multiple variables more independent and minimizing the feature redundancy. We also incorporate a contrastive learning approach to maximize the feature invariance under different data augmentations of the same point cloud. Experimental results show that our approach outperforms previous unsupervised learning methods on the downstream task of 3D point cloud classification and segmentation.