Skip to main content

Zero-shot learning via class-conditioned deep generative models

Publication ,  Conference
Wang, W; Pu, Y; Verma, VK; Fan, K; Zhang, Y; Chen, C; Rai, P; Carin, L
Published in: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
January 1, 2018

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.

Duke Scholars

Published In

32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Publication Date

January 1, 2018

Start / End Page

4211 / 4218
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, W., Pu, Y., Verma, V. K., Fan, K., Zhang, Y., Chen, C., … Carin, L. (2018). Zero-shot learning via class-conditioned deep generative models. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 4211–4218).
Wang, W., Y. Pu, V. K. Verma, K. Fan, Y. Zhang, C. Chen, P. Rai, and L. Carin. “Zero-shot learning via class-conditioned deep generative models.” In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, 4211–18, 2018.
Wang W, Pu Y, Verma VK, Fan K, Zhang Y, Chen C, et al. Zero-shot learning via class-conditioned deep generative models. In: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. 2018. p. 4211–8.
Wang, W., et al. “Zero-shot learning via class-conditioned deep generative models.” 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, 2018, pp. 4211–18.
Wang W, Pu Y, Verma VK, Fan K, Zhang Y, Chen C, Rai P, Carin L. Zero-shot learning via class-conditioned deep generative models. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. 2018. p. 4211–4218.

Published In

32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Publication Date

January 1, 2018

Start / End Page

4211 / 4218