Zero-Shot Learning via Class-Conditioned Deep Generative Models


  • Wenlin Wang Duke University
  • Yunchen Pu Duke University
  • Vinay Verma IIT Kanpur
  • Kai Fan Duke University
  • Yizhe Zhang Duke University
  • Changyou Chen SUNY at Buffalo
  • Piyush Rai IIT Kanpur
  • Lawrence Carin Duke University



We present a deep generative model for Zero-Shot Learning (ZSL). Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen class using a class-specific latent-space distribution, conditioned on class attributes. We use these latent-space distributions as a prior for a supervised variational autoencoder (VAE), which also facilitates learning highly discriminative feature representations for the inputs. The entire framework is learned end-to-end using only the seen-class training data. At test time, the label for an unseen-class test input is the class that maximizes the VAE lower bound. We further extend the model to a (i) semi-supervised/transductive setting by leveraging unlabeled unseen-class data via an unsupervised learning module, and (ii) few-shot learning where we also have a small number of labeled inputs from the unseen classes. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of benchmark data sets.




How to Cite

Wang, W., Pu, Y., Verma, V., Fan, K., Zhang, Y., Chen, C., Rai, P., & Carin, L. (2018). Zero-Shot Learning via Class-Conditioned Deep Generative Models. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).