Relation-based Discriminative Cooperation Network for Zero-Shot Classification

Yang Liu*, Xinbo Gao, Quanxue Gao, Jungong Han, Ling Shao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

16 Citations (SciVal)
85 Downloads (Pure)

Abstract

Zero-shot learning (ZSL) aims to assign the category corresponding to the relevant semantic as the label of the unseen sample based on the relationship between the learned visual and semantic features. However, most typical ZSL models faced with the domain bias problem, which leads to unseen or test samples being easily misclassified into seen or training categories. To handle this problem, we propose a relation-based discriminative cooperation network (RDCN) model for ZSL in this work. The proposed model effectively utilize the robust metric space spanned by the cooperated semantics with the help of a set of relations. On the other hand, we devise the relation network to measure the relationship between the visual features and embedded semantics, and the validation information will guide the embedding module to learn more discriminative information. At last, the proposed RDCN model is validated on six benchmarks, and extensive experiments demonstrate the superiority of proposed method over most existing ZSL models on the traditional zero-shot setting and the more realistic generalized zero-shot setting.

Original languageEnglish
Article number108024
JournalPattern Recognition
Volume118
Early online date28 May 2021
DOIs
Publication statusPublished - 01 Oct 2021

Keywords

  • Bias
  • Discriminative
  • Relation
  • Zero-shot learning

Fingerprint

Dive into the research topics of 'Relation-based Discriminative Cooperation Network for Zero-Shot Classification'. Together they form a unique fingerprint.

Cite this