Zero Shot Deep Learning from Semantic Attributes
ICMLA, pp. 871-876, 2015.
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
Full Text (Upload PDF)
PPT (Upload PPT)