mlsanityData to 7 Oct 2026

Towards Visual Taxonomy Expansion

arXiv 2309.06105 ↗First posted 12 Sep 2023cs.CV cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual semantics, leading to an inability to generalize to unseen terms and the "Prototypical Hypernym Problem." In this paper, we propose Visual Taxonomy Expansion (VTE), introducing visual features into the taxonomy expansion task. We propose a textual hypernymy learning task and a visual prototype learning task to cluster textual and visual semantics. In addition to the tasks on respective modalities, we introduce a hyper-proto constraint that integrates textual and visual semantics to produce fine-grained visual semantics. Our method is evaluated on two datasets, where we obtain compelling results. Specifically, on the Chinese taxonomy dataset, our method significantly improves accuracy by 8.75 %. Additionally, our approach performs better than ChatGPT on the Chinese taxonomy dataset.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 35 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

17 of 35 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  6. 2020TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Networkcited by 37
  7. 2020STEAM: Self-Supervised Taxonomy Expansion with Mini-Pathscited by 31
  8. 2016Improving Hypernymy Detection with an Integrated Path-based and Distributional Methodcited by 26
  9. 2019SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemblecited by 25
  10. 2021Temperature as Uncertainty in Contrastive Learningcited by 25
  11. 2021Taxonomy Completion via Triplet Matching Networkcited by 21
  12. 2022TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representationscited by 20
5 more
  1. 2021Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representationscited by 19
  2. 2018End-to-End Reinforcement Learning for Automatic Taxonomy Inductioncited by 17
  3. 2021HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learningcited by 14
  4. 2021Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansioncited by 6
  5. 2022Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervisioncited by 4

Built on by

Not cited yet.