2 papers
cs.LG2019
Implicit Discriminator in Variational Autoencoder
Prateek Munjal, Akanksha Paul, Narayanan C. Krishnan
Recently generative models have focused on combining the advantages of variational autoencoders (VAE) and generative adversarial networks (GAN) for good reconstruction and generati…
cs.CV2019
Semantically Aligned Bias Reducing Zero Shot Learning
Akanksha Paul, Narayanan C. Krishnan, Prateek Munjal
Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the h…