English

DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors

Computer Vision and Pattern Recognition 2020-07-01 v2

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.

Keywords

Cite

@article{arxiv.2006.05895,
  title  = {DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors},
  author = {Sarthak Bhagat and Vishaal Udandarao and Shagun Uppal},
  journal= {arXiv preprint arXiv:2006.05895},
  year   = {2020}
}

Comments

Published at the 37th International Conference on Machine Learning (ICML 2020) Workshop on ML Interpretability for Scientific Discovery

R2 v1 2026-06-23T16:12:40.035Z