Hierarchical-Dynamic Embedding for Zero-Shot Object Recognition

Xuebo Han, Kan Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Zero-shot object recognition is aiming to attach unseen category labels to images which are out of the training set. The key challenge in Zero-shot learning is building the map between visual domain and semantic domain. However, previous Visual-Semantic Embedding ignores the essential difference between the vectors of category names and the vectors of the entities. Hybrid model, moreover, computes the middle vector with a fixed size candidate set which limits the generalization on different images. So we propose a novel framework named Hierarchical-Dynamic Embedding. First, Hierarchical Network Embedding (HNE) takes advantage of the internal hierarchical taxonomy of the category names. We then provide Dynamic Hybrid Model (DHM) to map unseen images from visual vectors to entity vectors. Furthermore, we conduct the experiments on 1,000 seen categories and 1,548 unseen categories to show the state-of-the-art performance of our proposed framework.

Original languageEnglish
Title of host publicationProceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
EditorsFernando G. Tinetti, Quoc-Nam Tran, Leonidas Deligiannidis, Mary Qu Yang, Mary Qu Yang, Hamid R. Arabnia
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages520-525
Number of pages6
ISBN (Electronic)9781538626528
DOIs
Publication statusPublished - 4 Dec 2018
Event2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017 - Las Vegas, United States
Duration: 14 Dec 201716 Dec 2017

Publication series

NameProceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017

Conference

Conference2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
Country/TerritoryUnited States
CityLas Vegas
Period14/12/1716/12/17

Keywords

  • Entity embedding
  • Object recognition
  • Transfer learning
  • Visual-Semantic Embedding
  • Zero-shot learning

Fingerprint

Dive into the research topics of 'Hierarchical-Dynamic Embedding for Zero-Shot Object Recognition'. Together they form a unique fingerprint.

Cite this