Unsupervised Multi-Task Feature Learning on Point Clouds

Kaveh Hassani, Mike Haley; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 8160-8171

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%.

Related Material


[pdf]
[bibtex]
@InProceedings{Hassani_2019_ICCV,
author = {Hassani, Kaveh and Haley, Mike},
title = {Unsupervised Multi-Task Feature Learning on Point Clouds},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}