DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors

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.

Publication
Workshop on ML Interpretability for Scientific Discovery (ICML) 2020, Workshop on Perception Through Structured Generative Models (ECCV) 2020
Date
Links
PDF Slides Video Code

Please cite using following bibtex:

@article{Bhagat2020DisContSV,
  title={DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors},
  author={Sarthak Bhagat and Vishaal Udandarao and Shagun Uppal},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.05895}
}