Disentangling by Factorising

ICML 2018  ·  Hyunjik Kim, andriy mnih ·

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon $\beta$-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

PDF Abstract ICML 2018 PDF ICML 2018 Abstract


Introduced in the Paper:

3D Shapes Dataset

Used in the Paper:

CelebA 3D Chairs Chairs

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here