Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification
This addresses the problem of limited labeled data in image classification for AI/ML practitioners, though it appears incremental as it builds on existing few-shot learning and knowledge integration methods.
The authors tackled few-shot image classification by integrating ontology-based background knowledge as n-ball concept embeddings into a neural vision architecture, achieving superior performance on two standard benchmarks.
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.