Bi-shifting semantic auto-encoder for zero-shot learning

Bi-shifting semantic auto-encoder for zero-shot learning

Zero-shot learning aims to transfer the model of labeled seen classes in the source domain to the disjoint unseen classes without annotations in the target domain. Most existing approaches generally consider directly adopting the visual-semantic projection function learned in the source domain to th...

Full description

Bibliographic Details
Main Author: Yu Wang
Format: Article
Language:English
Published: AIMS Press 2022-01-01
Series:Electronic Research Archive
Subjects:
zero-shot learning
auto-encoder
projection learning
semantic representation
domain adaptation
Online Access:https://www.aimspress.com/article/doi/10.3934/era.2022008?viewType=HTML

Internet

https://www.aimspress.com/article/doi/10.3934/era.2022008?viewType=HTML

Similar Items