Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding
This addresses the need for more robust and efficient unsupervised learning in 3D computer vision, offering a novel approach that avoids the pitfalls of data augmentation, though it is incremental within the field.
The paper tackles the problem of data augmentation dependency in unsupervised learning for 3D point clouds by proposing SoftClu, an augmentation-free method that uses soft clustering and optimal transport to learn point-level features, achieving state-of-the-art results in tasks like 3D object classification and segmentation.
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.