Disentangling Factors of Variation with Cycle-Consistent Variational AutoEncoders

Ananya Harsh Jha, Saket Anand, Maneesh Singh, V. S. R. Veeravasarapu
ECCV 2018

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently generate new data necessary for a particular task. Learning disentangled representations is a challenging problem, especially when certain factors of variation are difficult to label. In this paper, we introduce a novel architecture that disentangles the latent space into two complementary subspaces by using only weak supervision in form of pairwise similarity labels. Inspired by the recent success of cycle-consistent adversarial architectures, we use cycle-consistency in a variational auto-encoder framework. Our non-adversarial approach is in contrast with the recent works that combine adversarial training with auto-encoders to disentangle representations. We show compelling results of disentangled latent subspaces on three datasets and compare with recent works that leverage adversarial training.

[code] [poster (coming soon…)]


  • We highlight the limitations of recently proposed adversarial architectures
  • Novel architecture called Cycle-consistent VAEs disentangle specified and unspecified factors of variation using only pairwise similarity labels
  • Our architecture is also unique in being robust to the choice of dimensionality of the latent codes
  • Our loss functions explicitly train the encoder to produce highly disentangled representations


Leave a Reply