Unsupervised Multi-Task Feature Learning on Point Clouds

Kaveh Hassani; Mike Haley

ICCV 2019poster239 citations

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%.

BibTeX

@inproceedings{iccv2019_unsupervisedmult,
  title = {Unsupervised Multi-Task Feature Learning on Point Clouds},
  author = {Kaveh Hassani and Mike Haley},
  booktitle = {ICCV 2019},
  year = {2019}
}