Knowledge-aware Zero-Shot Learning: Survey and Perspective
This is an incremental survey paper for researchers in machine learning, focusing on knowledge-aware approaches to ZSL.
The paper surveys zero-shot learning (ZSL) methods that use external knowledge to predict unseen classes, categorizing and comparing different types of knowledge and discussing future roles of symbolic knowledge in addressing sample shortage issues.
Zero-shot learning (ZSL) which aims at predicting classes that have never appeared during the training using external knowledge (a.k.a. side information) has been widely investigated. In this paper we present a literature review towards ZSL in the perspective of external knowledge, where we categorize the external knowledge, review their methods and compare different external knowledge. With the literature review, we further discuss and outlook the role of symbolic knowledge in addressing ZSL and other machine learning sample shortage issues.