DisCont: Self-Supervised Visual Attribute Disentanglement Using Context Vectors

Sarthak Bhagat, Vishaal Udandarao, Shagun Uppal, Saket Anand

ECCVW 2020 pp. 549-553

doi:10.1007/978-3-030-65414-6_38 /eccvw/2020/bhagat2020eccvw-discont/

Abstract

Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well provide greater interpretability and control. In this paper, we propose a self-supervised framework DisCont to disentangle multiple attributes by exploiting the structural inductive biases within images. Motivated by the recent surge in contrastive learning paradigms, our model bridges the gap between self-supervised contrastive learning algorithms and unsupervised disentanglement. We evaluate the efficacy of our approach, both qualitatively and quantitatively, on four benchmark datasets.

PDF ECCVW Semantic Scholar

Cite

Text

Bhagat et al. "DisCont: Self-Supervised Visual Attribute Disentanglement Using Context Vectors." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-65414-6_38

Markdown

[Bhagat et al. "DisCont: Self-Supervised Visual Attribute Disentanglement Using Context Vectors." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/bhagat2020eccvw-discont/) doi:10.1007/978-3-030-65414-6_38

BibTeX

@inproceedings{bhagat2020eccvw-discont,
  title     = {{DisCont: Self-Supervised Visual Attribute Disentanglement Using Context Vectors}},
  author    = {Bhagat, Sarthak and Udandarao, Vishaal and Uppal, Shagun and Anand, Saket},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {549-553},
  doi       = {10.1007/978-3-030-65414-6_38},
  url       = {https://mlanthology.org/eccvw/2020/bhagat2020eccvw-discont/}
}