2017/11/15 · We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, ...

Abstract. We present a deep generative model for Zero-Shot Learn- ing (ZSL). Unlike most existing methods for this problem, that represent each class as a ...

A deep generative model for Zero-Shot Learning that represents each seen/unseen class using a class-specific latent-space distribution, conditioned on class ...

We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent ...

Zero-Shot Learning via Class-Conditioned Deep Generative Models. Published in AAAI, 2018. Recommended citation: Wenlin Wang, Yunchen Pu, Vinay Kumar Verma ...

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 ...

2018/01/01 · We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of benchmark data sets.

We train a Conditional Variational Autoencoder to learn the underlying probability distribution of the im- age features(X) conditioned on the class embedding.

Fingerprint. Dive into the research topics of 'Zero-shot learning via class-conditioned deep generative models'. Together they form a unique fingerprint.

2018/02/06 · Zero-shot learning with generative latent prototype model. arXiv preprint arXiv:1705.09474, 2017. Tomas Mikolov, Ilya Sutskever, Kai Chen ...