Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification

Abstract

We propose a novel framework named ViOCE that integrates ontology-based background knowledge in the form of $n$-ball concept embeddings into a neural network based vision architecture. The approach consists of two components - converting symbolic knowledge of an ontology into continuous space by learning n-ball embeddings that capture properties of subsumption and disjointness, and guiding the training and inference of a vision model using the learnt embeddings. We evaluate ViOCE using the task of few-shot image classification, where it demonstrates superior performance on two standard benchmarks.

References in corpus (8)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Harnessing Deep Neural Networks with Logic Rules
• Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
• An Evaluation of Knowledge Graph Embeddings for Autonomous Driving Data: Experience and Practice
• Visual-Semantic Embedding Model Informed by Structured Knowledge