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

09/19/2021
by   Mirantha Jayathilaka, et al.
12

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/06/2022

KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles

We propose KGTN-ens, a framework extending the recent Knowledge Graph Tr...
research
09/21/2020

Visual-Semantic Embedding Model Informed by Structured Knowledge

We propose a novel approach to improve a visual-semantic embedding model...
research
06/08/2022

Disentangled Ontology Embedding for Zero-shot Learning

Knowledge Graph (KG) and its variant of ontology have been widely used f...
research
06/30/2020

Ontology-guided Semantic Composition for Zero-Shot Learning

Zero-shot learning (ZSL) is a popular research problem that aims at pred...
research
02/19/2019

DeepBall: Deep Neural-Network Ball Detector

The paper describes a deep network based object detector specialized for...
research
08/15/2023

Synthesizing Political Zero-Shot Relation Classification via Codebook Knowledge, NLI, and ChatGPT

Recent supervised models for event coding vastly outperform pattern-matc...
research
12/14/2020

Lagrangian Reachtubes: The Next Generation

We introduce LRT-NG, a set of techniques and an associated toolset that ...

Please sign up or login with your details

Forgot password? Click here to reset