Ananya Harsh Jha
Research Subjects
Research Interests
Ananya Harsh Jha has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Maneesh Singh
Verisk Analytics
1 shared publication- Maneesh Singh
Verisk Analytics
1 shared publication Saket Anand
IIIT-Delhi
1 shared publication- Saket Anand
Indraprastha Institute of Information Technology Delhi India
1 shared publication - V. S. R. Veeravasarapu
Verisk AI Verisk Analytics
1 shared publication Vsr Veeravasarapu
Verisk Analytics
1 shared publication
Latest Publications
- 7 October 2018
- Published by Springer Nature
- p. 829-845
Disentangling Factors of Variation with Cycle-Consistent Variational Auto-encoders
- 7 October 2018
- Published by Springer Nature
- p. 829-845
Disentangling Factors of Variation with Cycle-Consistent Variational Auto-encoders
- Open Access
Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders
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.
Open AccessDisentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders
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.