Zero-shot multi-label learning via label factorisation

被引:3
|
作者
Shao, Hang [1 ]
Guo, Yuchen [2 ]
Ding, Guiguang [2 ]
Han, Jungong [3 ]
机构
[1] Zhejiang Future Technol Inst Jiaxing, Jiaxing, Zhejiang, Peoples R China
[2] Tsinghua Univ, Sch Software, Beijing, Peoples R China
[3] Univ Lancaster, Sch Comp & Commun, Lancaster, England
关键词
D O I
10.1049/iet-cvi.2018.5131
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This study considers the zero-shot learning problem under the multi-label setting where each test sample is associated with multiple labels that are unseen in training data. The authors propose a novel learning framework based on label factorisation for this problem. Specifically, the authors' framework takes three key issues into consideration and addresses them in a unified way. The first is knowledge transfer that utilises information from seen classes to build recognition models for unseen classes. The second is label correlation which means that labels which have different semantics may co-occur frequently. This is an important issue in multi-label learning. The authors propose to learn a shared latent space by label factorisation and use the label semantics as the decoding function, which can address both issues. The third is the predictability which requires the learned latent space to be strongly related to the visual features. It is guaranteed by incorporating a regression model into the learning framework. The authors derive two specific formulations from the general framework and propose the corresponding learning algorithms. The authors conducted extensive experiments on three multi-label data sets. The results demonstrated the effectiveness.
引用
收藏
页码:117 / 124
页数:8
相关论文
empty
未找到相关数据