Zero‐shot learning by exploiting class‐related and attribute‐related prior knowledge

Zero‐shot learning by exploiting class‐related and attribute‐related prior knowledge

The existing attribute‐based zero‐shot learning models at different levels ignore some necessary prior knowledge. It is essential to improve classification accuracy of zero‐shot learning that how to mine attribute‐related and class‐related prior knowledge further being incorporated into the attribut...

Full description

Bibliographic Details
Main Authors: Xuesong Wang, Chen Chen, Yuhu Cheng
Format: Article
Language:English
Published: Wiley 2016-09-01
Series:IET Computer Vision
Subjects:
class-related prior knowledge
attribute-related prior knowledge
attribute-based zero-shot learning model
zero-shot learning classification
class-related prior knowledge mining
attribute prediction model
Online Access:https://doi.org/10.1049/iet-cvi.2015.0131

Internet

https://doi.org/10.1049/iet-cvi.2015.0131

Similar Items