ML Anthology

A Two-Step Disentanglement Method

Naama Hadad, Lior Wolf, Moni Shahar
CVPR 2018
doi:10.1109/CVPR.2018.00087 /cvpr/2018/hadad2018cvpr-twostep/

Abstract

We address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not. Our solution is simpler than previous solutions and employs adversarial training. First, the part of the data that is correlated with the labels is extracted by training a classifier. Then, the other part is extracted such that it enables the reconstruction of the original data but does not contain label information. The utility of the new method is demonstrated on visual datasets as well as on financial data. Our code is available at https://github.com/naamahadad/A-Two-Step-Disentanglement-Method.

PDF CVPR Semantic Scholar

Cite

Text

Hadad et al. "A Two-Step Disentanglement Method." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00087

Markdown

[Hadad et al. "A Two-Step Disentanglement Method." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/hadad2018cvpr-twostep/) doi:10.1109/CVPR.2018.00087

BibTeX

@inproceedings{hadad2018cvpr-twostep,
  title     = {{A Two-Step Disentanglement Method}},
  author    = {Hadad, Naama and Wolf, Lior and Shahar, Moni},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00087},
  url       = {https://mlanthology.org/cvpr/2018/hadad2018cvpr-twostep/}
}