mlsanityData to 14 Oct 2026

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

arXiv 2109.09063 ↗First posted 19 Sep 2021cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 19 Sep 2021.

Builds on

16 of 28 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  8. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  9. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  10. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  11. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  12. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 74
4 more
  1. 2016The More You Know: Using Knowledge Graphs for Image Classificationcited by 63
  2. 2019EL Embeddings: Geometric construction of models for the Description Logic EL ++cited by 48
  3. 2020An Evaluation of Knowledge Graph Embeddings for Autonomous Driving Data: Experience and Practicecited by 13
  4. 2020Visual-Semantic Embedding Model Informed by Structured Knowledgecited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 2.

4 papers.

  1. 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23
  2. 2022A Survey on Visual Transfer Learning using Knowledge Graphscited by 7
  3. 2023Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphscited by 4
  4. 2023Inspecting class hierarchies in classification-based metric learning modelscited by 1