Zero-shot learning (ZSL) is a popular research problem that aims at predicting for those classes that have never appeared in the training stage by utilizing the inter-class relationship with some side information. In this study, we propose to model the compositional and expressive semantics of class labels by an OWL (Web Ontology Language) ontology, and further develop a new ZSL framework with ontology embedding. The effectiveness has been verified by some primary experiments on animal image classification and visual question answering.
@article{arxiv.2006.16917,
title = {Ontology-guided Semantic Composition for Zero-Shot Learning},
author = {Jiaoyan Chen and Freddy Lecue and Yuxia Geng and Jeff Z. Pan and Huajun Chen},
journal= {arXiv preprint arXiv:2006.16917},
year = {2020}
}
Comments
Accepted by KR 2020 - 17th International Conference on Principles of Knowledge Representation and Reasoning