DeepAI AI Chat
Log In Sign Up

Self-Supervised Few-Shot Learning on Point Clouds

by   Charu Sharma, et al.

The increased availability of massive point clouds coupled with their utility in a wide variety of applications such as robotics, shape synthesis, and self-driving cars has attracted increased attention from both industry and academia. Recently, deep neural networks operating on labeled point clouds have shown promising results on supervised learning tasks like classification and segmentation. However, supervised learning leads to the cumbersome task of annotating the point clouds. To combat this problem, we propose two novel self-supervised pre-training tasks that encode a hierarchical partitioning of the point clouds using a cover-tree, where point cloud subsets lie within balls of varying radii at each level of the cover-tree. Furthermore, our self-supervised learning network is restricted to pre-train on the support set (comprising of scarce training examples) used to train the downstream network in a few-shot learning (FSL) setting. Finally, the fully-trained self-supervised network's point embeddings are input to the downstream task's network. We present a comprehensive empirical evaluation of our method on both downstream classification and segmentation tasks and show that supervised methods pre-trained with our self-supervised learning method significantly improve the accuracy of state-of-the-art methods. Additionally, our method also outperforms previous unsupervised methods in downstream classification tasks.


page 5

page 12

page 16

page 17

page 18

page 19

page 20

page 21


Point2Vec for Self-Supervised Representation Learning on Point Clouds

Recently, the self-supervised learning framework data2vec has shown insp...

Context Prediction for Unsupervised Deep Learning on Point Clouds

Point clouds provide a flexible and natural representation usable in cou...

MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds

We present a self-supervised task on point clouds, in order to learn mea...

SurFit: Learning to Fit Surfaces Improves Few Shot Learning on Point Clouds

We present SurFit, a simple approach for label efficient learning of 3D ...

Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation

Point clouds upsampling is a challenging issue to generate dense and uni...

Contrastive Self-Supervised Learning for Skeleton Representations

Human skeleton point clouds are commonly used to automatically classify ...

Code Repositories