Ontology-guided Semantic Composition for Zero-Shot Learning

Jiaoyan Chen, Freddy Lecue, Yuxia Geng, Jeff Z. Pan, Huajun Chen

Research output: Working paper

Abstract

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 ani- mal image classification and visual question answering.
Original languageEnglish
PublisherArXiv
Number of pages5
Publication statusSubmitted - 30 Jun 2020

Fingerprint Dive into the research topics of 'Ontology-guided Semantic Composition for Zero-Shot Learning'. Together they form a unique fingerprint.

Cite this