Ontology-guided Semantic Composition for Zero-Shot Learning

2020-06-30Code Available1· sign in to hype

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

Code Available — Be the first to reproduce this paper.

Code

github.com/China-UK-ZSL/Resources_for_KZSL
pytorch★ 28

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 animal image classification and visual question answering.

Tasks

image-classification Image Classification Ontology Embedding Question Answering Semantic Composition Visual Question Answering Visual Question Answering (VQA)Zero-Shot Learning

Ontology-guided Semantic Composition for Zero-Shot Learning

Code

Abstract

Tasks

Reproductions