Unsupervised Multi-Task Feature Learning on Point Clouds

Abstract

We introduce an unsupervised multi-task model to jointly learn point and shape features on point clouds. We define three unsupervised tasks including clustering, reconstruction, and self-supervised classification to train a multi-scale graph-based encoder. We evaluate our model on shape classification and segmentation benchmarks. The results suggest that it outperforms prior state-of-the-art unsupervised models: In the ModelNet40 classification task, it achieves an accuracy of 89.1% and in ShapeNet segmentation task, it achieves an mIoU of 68.2 and accuracy of 88.6%.

Cite

Text

Hassani and Haley. "Unsupervised Multi-Task Feature Learning on Point Clouds." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00825

Markdown

[Hassani and Haley. "Unsupervised Multi-Task Feature Learning on Point Clouds." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/hassani2019iccv-unsupervised/) doi:10.1109/ICCV.2019.00825

BibTeX

@inproceedings{hassani2019iccv-unsupervised,
  title     = {{Unsupervised Multi-Task Feature Learning on Point Clouds}},
  author    = {Hassani, Kaveh and Haley, Mike},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00825},
  url       = {https://mlanthology.org/iccv/2019/hassani2019iccv-unsupervised/}
}