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.



There are no comments yet.


page 5

page 12

page 16

page 17

page 18

page 19

page 20

page 21


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 ...

Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges

Point cloud processing and 3D shape understanding are very challenging t...

Using Cross-Loss Influence Functions to Explain Deep Network Representations

As machine learning is increasingly deployed in the real world, it is ev...

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

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

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds

To date, various 3D scene understanding tasks still lack practical and g...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.