Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

TL;DR

This paper introduces SoftClu, an augmentation-free unsupervised learning method for 3D point clouds that uses soft clustering and optimal transport to learn transferable features without data augmentation.

Contribution

We propose SoftClu, a novel augmentation-free approach that leverages soft clustering and optimal transport for unsupervised 3D point cloud learning, avoiding the pitfalls of data augmentation.

Findings

Outperforms state-of-the-art methods on 3D classification tasks.

Effective in part and semantic segmentation.

Reduces reliance on data augmentation techniques.

Abstract

Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods. However, data augmentation is not ideal as it requires a careful selection of the type of augmentations to perform, which in turn can affect the geometric and semantic information learned by the network during self-training. To overcome this issue, we propose an augmentation-free unsupervised approach for point clouds to learn transferable point-level features via soft clustering, named SoftClu. SoftClu assumes that the points belonging to a cluster should be close to each other in both geometric and feature spaces. This differs from typical contrastive learning, which builds similar representations for a whole point cloud and its augmented versions. We exploit the affiliation of points to their clusters as a proxy to enable self-training through a pseudo-label prediction task. Under the constraint that these pseudo-labels induce the equipartition of the point cloud, we cast SoftClu as an optimal transport problem. We formulate an unsupervised loss to minimize the standard cross-entropy between pseudo-labels and predicted labels. Experiments on downstream applications, such as 3D object classification, part segmentation, and semantic segmentation, show the effectiveness of our framework in outperforming state-of-the-art techniques.