The proposed sample probing approach improves the ZSL results even when integrated into state-of-the-art generative models, and opens doors to end-to-end training thanks to the differentiability of the solvers.
Authors
R. G. Cinbis
7 papers
Samet Çetin
1 papers
Orhun Bugra Baran
1 papers
Views
Field of Study
Computer Science
Venue Information
Name
International Conference on Learning Representations