A domain classifier trained in a joint visual-semantic latent space improves generalized zero-shot learning results by a small margin over CADA-VAE and cycle-WGAN baselines.
Devise: A deep visual- semantic embedding model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generalised Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space
A domain classifier trained in a joint visual-semantic latent space improves generalized zero-shot learning results by a small margin over CADA-VAE and cycle-WGAN baselines.