# Self-Supervised Few-Shot Learning on Point Clouds

arXiv: https://arxiv.org/abs/2009.14168 · HTML: https://mlsanity.com/paper/2009.14168/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 30 of 66)

- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding](https://mlsanity.com/paper/2305.10764/) (2023)
- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [Self-Supervised Learning for Videos: A Survey](https://mlsanity.com/paper/2207.00419/) (2022)
- [CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data](https://mlsanity.com/paper/2303.12417/) (2023)
- [SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds](https://mlsanity.com/paper/2104.04891/) (2021)
- [Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model](https://mlsanity.com/paper/2404.14966/) (2024)
- [Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis](https://mlsanity.com/paper/2303.08134/) (2023)
- [GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions](https://mlsanity.com/paper/2206.02780/) (2022)
- [Masked Autoencoders in 3D Point Cloud Representation Learning](https://mlsanity.com/paper/2207.01545/) (2022)
- [Point2Vec for Self-Supervised Representation Learning on Point Clouds](https://mlsanity.com/paper/2303.16570/) (2023)
- [Multimodal Semi-Supervised Learning for 3D Objects](https://mlsanity.com/paper/2110.11601/) (2021)
- [PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders](https://mlsanity.com/paper/2408.08753/) (2024)
- [Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey](https://mlsanity.com/paper/2305.04691/) (2023)
- [3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.14084/) (2022)
- [ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation](https://mlsanity.com/paper/2311.14262/) (2023)
- [No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation](https://mlsanity.com/paper/2404.04050/) (2024)
- [LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2211.05997/) (2022)
- [Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview](https://mlsanity.com/paper/2211.08352/) (2022)
- [Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection](https://mlsanity.com/paper/2210.05593/) (2022)
- [A Survey of Generative Techniques for Spatial-Temporal Data Mining](https://mlsanity.com/paper/2405.09592/) (2024)
- [Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition](https://mlsanity.com/paper/2308.09694/) (2023)
- [Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2310.20293/) (2023)
- [A Closer Look at Few-Shot 3D Point Cloud Classification](https://mlsanity.com/paper/2303.18210/) (2023)
- [Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2211.06841/) (2022)
- [ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion](https://mlsanity.com/paper/2303.01979/) (2023)
- [Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis](https://mlsanity.com/paper/2210.15904/) (2022)
- [ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understanding](https://mlsanity.com/paper/2303.14376/) (2023)

## Abstract (arXiv)

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.