Disentangling by Factorising
2018-02-16ICML 2018Code Available1· sign in to hype
Hyunjik Kim, andriy mnih
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/mmrl/disent-and-genpytorch★ 21
- github.com/OZA15015/custom_FVAEpytorch★ 0
- github.com/AliLotfi92/Disentangling-by-Factorisingpytorch★ 0
- github.com/AliLotfi92/Disentangling_by_Factorisingpytorch★ 0
- github.com/1Konny/FactorVAEpytorch★ 0
- github.com/danielbraithwt/Readingsnone★ 0
- github.com/nicolasigor/FactorVAEtf★ 0
- github.com/gene-chou/conditional-factor-vaepytorch★ 0
- github.com/Michedev/FactorVAEpytorch★ 0
- github.com/Guiliang/FactorVAEpytorch★ 0
Abstract
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 -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.