ML Anthology

Self-Supervision for 3D Real-World Challenges

Antonio Alliegro, Davide Boscaini, Tatiana Tommasi
ECCVW 2020 pp. 704-708
doi:10.1007/978-3-030-66415-2_48 /eccvw/2020/alliegro2020eccvw-selfsupervision/

Abstract

We consider several possible scenarios involving synthetic and real-world point clouds where supervised learning fails due to data scarcity and large domain gaps. We propose to enrich standard feature representations by leveraging self-supervision through a multi-task model that can solve a 3D puzzle while learning the main task of shape classification or part segmentation.

PDF ECCVW Semantic Scholar

Cite

Text

Alliegro et al. "Self-Supervision for 3D Real-World Challenges." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-66415-2_48

Markdown

[Alliegro et al. "Self-Supervision for 3D Real-World Challenges." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/alliegro2020eccvw-selfsupervision/) doi:10.1007/978-3-030-66415-2_48

BibTeX

@inproceedings{alliegro2020eccvw-selfsupervision,
  title     = {{Self-Supervision for 3D Real-World Challenges}},
  author    = {Alliegro, Antonio and Boscaini, Davide and Tommasi, Tatiana},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {704-708},
  doi       = {10.1007/978-3-030-66415-2_48},
  url       = {https://mlanthology.org/eccvw/2020/alliegro2020eccvw-selfsupervision/}
}