Corpus ID: 221995690

Self-Supervised Few-Shot Learning on Point Clouds

@article{Sharma2020SelfSupervisedFL,
  title={Self-Supervised Few-Shot Learning on Point Clouds},
  author={Charu Sharma and Manohar Kaul},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.14168}
}
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… Expand
Generating Point Cloud from Single Image in The Few Shot Scenario
TLDR
This work proposes a novel few-shot single-view point cloud generation framework by considering both class-specific and class-agnostic 3D shape priors, which outperforms state-of-the-art methods in the few- shot setting. Expand
Unsupervised Point Cloud Pre-Training via Occlusion Completion
TLDR
This paper shows that this method outperforms previous pre-training methods in object classification, and both part-based and semantic segmentation tasks, and even when it pre-train on a single dataset (ModelNet40), improves accuracy across different datasets and encoders. Expand
Multimodal Semi-Supervised Learning for 3D Objects
  • Zhimin Chen, Longlong Jing, Yang Liang, YingLi Tian, Bing Li
  • Computer Science
  • ArXiv
  • 2021
TLDR
This paper proposes a novel multimodal semi-supervised learning framework by introducing instance-level consistency constraint and a novel multi-modality contrastive prototype (M2CP) loss. Expand
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
  • Xumin Yu, Lulu Tang, Yongming Rao, Tiejun Huang, Jie Zhou, Jiwen Lu
  • Computer Science
  • ArXiv
  • 2021
We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT [8] to 3D point cloud. Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-trainExpand
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds with 1000x Fewer Labels
TLDR
A new weak supervision method to implicitly augment the total amount of available supervision signals, by leveraging the semantic similarity between neighboring points, is proposed, achieving state-of-the-art performance on six large-scale open datasets under weak supervision schemes. Expand
Overcoming Failures of Imagination in AI Infused System Development and Deployment
TLDR
It is argued that frameworks of harms must be context-aware and consider a wider range of potential stakeholders, system affordances, as well as viable proxies for assessing harms in the widest sense to effectively assist in anticipating harmful uses. Expand

References

SHOWING 1-10 OF 26 REFERENCES
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space
TLDR
This work proposes a self-supervised learning task for deep learning on raw point cloud data in which a neural network is trained to reconstruct point clouds whose parts have been randomly rearranged, and demonstrates that pre-training with this method before supervised training improves the performance of state-of-the-art models and significantly improves sample efficiency. Expand
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
TLDR
A novel end-to-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds, and is shown, in theory, to be a generic architecture that is able to reconstruct an arbitrary point cloud from a 2D grid. Expand
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
TLDR
A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly. Expand
Dynamic Graph CNN for Learning on Point Clouds
TLDR
This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network. Expand
PointCNN: Convolution On X-Transformed Points
TLDR
This work proposes to learn an Χ-transformation from the input points to simultaneously promote two causes: the first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Expand
Learning Representations and Generative Models for 3D Point Clouds
TLDR
A deep AutoEncoder network with state-of-the-art reconstruction quality and generalization ability is introduced with results that outperform existing methods on 3D recognition tasks and enable shape editing via simple algebraic manipulations. Expand
Unsupervised Learning of Shape and Pose with Differentiable Point Clouds
TLDR
This work trains a convolutional network to predict both the shape and the pose from a single image by minimizing the reprojection error, and introduces an ensemble of pose predictors which are distill to a single "student" model. Expand
Few-Shot Learning with Graph Neural Networks
TLDR
A graph neural network architecture is defined that generalizes several of the recently proposed few-shot learning models and provides improved numerical performance, and is easily extended to variants of few- shot learning, such as semi-supervised or active learning, demonstrating the ability of graph-based models to operate well on 'relational' tasks. Expand
Target-driven visual navigation in indoor scenes using deep reinforcement learning
TLDR
This paper proposes an actor-critic model whose policy is a function of the goal as well as the current state, which allows better generalization and proposes the AI2-THOR framework, which provides an environment with high-quality 3D scenes and a physics engine. Expand
...
1
2
3
...