Zero Shot Deep Learning from Semantic Attributes

ICMLA, pp. 871-876, 2015.

Cited by: 6|Bibtex|Views1|Links
EI

Abstract:

We study the problem of classifying images when no training exemplars are available for some image classes, and therefore direct classification is not possible. We use instead semantic attributes: if attributes of yet unseen classes can be determined, then class labels may themselves be decided based on prior knowledge of class to attribu...More

Code:

Data:

Your rating :
0

 

Tags
Comments