Unsupervised Disentanglement Learning by intervention

Weishen Pan, Sen Cui, Changshui Zhang

Keywords: Disentanglement, Intervention

Abstract: Recently there has been an increased interest in unsupervised learning of disentangled representations on the data generated from variation factors. Existing works rely on the assumption that the generative factors are independent despite this assumption is often violated in real-world scenarios. In this paper, we focus on the unsupervised learning of disentanglement in a general setting which the generative factors may be correlated. We propose an intervention-based framework to tackle this problem. In particular, first we apply a random intervention operation on a selected feature of the learnt image representation; then we propose a novel metric to measure the disentanglement by a downstream image translation task and prove it is consistent with existing ground-truth-required metrics experimentally; finally we design an end-to-end model to learn the disentangled representations with the self-supervision information from the downstream translation task. We evaluate our method on benchmark datasets quantitatively and give qualitative comparisons on a real-world dataset. Experiments show that our algorithm outperforms baselines on benchmark datasets when faced with correlated data and can disentangle semantic factors compared to baselines on real-world dataset.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=fXUJn9kn6