Relation-based Discriminative Cooperation Network for Zero-Shot Classification

PATTERN RECOGNITION

卷:118

Article

Liu, Yang¹  Gao, Xinbo^1,2  Gao, Quanxue¹  Han, Jungong³  Shao, Ling⁴ 

[1] Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Shaanxi, Peoples R China

[2] Chongqing Univ Posts & Telecommun, Chongqing Key Lab Image Cognit, Chongqing 400065, Peoples R China

[3] Aberystwyth Univ, Comp Sci Dept, Aberystwyth SY23 3FL, Dyfed, Wales

[4] Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates

关键词: Zero-shot learning;    Bias;    Discriminative;    Relation;   

DOI  :  10.1016/j.patcog.2021.108024

来源: Elsevier

【 摘 要 】

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. (c) 2021 Elsevier Ltd. All rights reserved.

【 授权许可】

Free