Corpus ID: 139101001

Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network

@article{Zhang2019UnsupervisedFL,
  title={Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network},
  author={Ling Zhang and Zhigang Zhu},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.12359}
}
  • Ling Zhang, Zhigang Zhu
  • Published in ArXiv 2019
  • Computer Science
  • To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud "3D object" dataset by using part contrasting and object clustering with deep graph neural networks (GNNs). In the contrast learning step, all the samples in the 3D object dataset are cut into two parts and put into a "part" dataset. Then a contrast learning GNN (ContrastNet) is trained to verify whether two randomly… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.

    Self-Supervised Learning for Domain Adaptation on Point-Clouds

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 39 REFERENCES

    FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    ShapeNet: An Information-Rich 3D Model Repository

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Dynamic Graph CNN for Learning on Point Clouds

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    On Visual Similarity Based 3D Model Retrieval

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL