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

Guofeng Mei ( University of Technology Sydney),* Cristiano Saltori (University of Trento), Fabio Poiesi (Fondazione Bruno Kessler), Jian Zhang (UTS), Elisa Ricci (University of Trento), Nicu Sebe (University of Trento), Qiang Wu (University of Technology Sydney)
The 33rd British Machine Vision Conference


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 aims to build 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 equipartition of the point cloud, we cast SoftClu as an optimal transport problem, which can be solved by using an efficient variant of the Sinkhorn-Knopp algorithm. 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, semantic segmentation, and part segmentation show the effectiveness of our framework, and that it can outperform state-of-the-art techniques.



author    = {Guofeng Mei and Cristiano Saltori and Fabio Poiesi and Jian Zhang and Elisa Ricci and Nicu Sebe and Qiang Wu},
title     = {Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year      = {2022},
url       = {}

Copyright © 2022 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection